CN117095381A - Traffic light matching method and device in automatic driving scene - Google Patents

Traffic light matching method and device in automatic driving scene Download PDF

Info

Publication number
CN117095381A
CN117095381A CN202311078689.5A CN202311078689A CN117095381A CN 117095381 A CN117095381 A CN 117095381A CN 202311078689 A CN202311078689 A CN 202311078689A CN 117095381 A CN117095381 A CN 117095381A
Authority
CN
China
Prior art keywords
matching
calculating
index
traffic lights
image
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Pending
Application number
CN202311078689.5A
Other languages
Chinese (zh)
Inventor
林伯昱
林金表
高强
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Jiuzhi Suzhou Intelligent Technology Co ltd
Original Assignee
Jiuzhi Suzhou Intelligent Technology Co ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Jiuzhi Suzhou Intelligent Technology Co ltd filed Critical Jiuzhi Suzhou Intelligent Technology Co ltd
Priority to CN202311078689.5A priority Critical patent/CN117095381A/en
Publication of CN117095381A publication Critical patent/CN117095381A/en
Pending legal-status Critical Current

Links

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V20/00—Scenes; Scene-specific elements
    • G06V20/50—Context or environment of the image
    • G06V20/56—Context or environment of the image exterior to a vehicle by using sensors mounted on the vehicle
    • G06V20/58—Recognition of moving objects or obstacles, e.g. vehicles or pedestrians; Recognition of traffic objects, e.g. traffic signs, traffic lights or roads
    • G06V20/584—Recognition of moving objects or obstacles, e.g. vehicles or pedestrians; Recognition of traffic objects, e.g. traffic signs, traffic lights or roads of vehicle lights or traffic lights
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00—Arrangements for image or video recognition or understanding
    • G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
    • G06V10/74—Image or video pattern matching; Proximity measures in feature spaces
    • G06V10/75—Organisation of the matching processes, e.g. simultaneous or sequential comparisons of image or video features; Coarse-fine approaches, e.g. multi-scale approaches; using context analysis; Selection of dictionaries
    • G06V10/751—Comparing pixel values or logical combinations thereof, or feature values having positional relevance, e.g. template matching
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00—Arrangements for image or video recognition or understanding
    • G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
    • G06V10/74—Image or video pattern matching; Proximity measures in feature spaces
    • G06V10/75—Organisation of the matching processes, e.g. simultaneous or sequential comparisons of image or video features; Coarse-fine approaches, e.g. multi-scale approaches; using context analysis; Selection of dictionaries
    • G06V10/758—Involving statistics of pixels or of feature values, e.g. histogram matching
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00—Arrangements for image or video recognition or understanding
    • G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
    • G06V10/766—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using regression, e.g. by projecting features on hyperplanes

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Multimedia (AREA)
  • Artificial Intelligence (AREA)
  • Health & Medical Sciences (AREA)
  • Computing Systems (AREA)
  • Databases & Information Systems (AREA)
  • Evolutionary Computation (AREA)
  • General Health & Medical Sciences (AREA)
  • Medical Informatics (AREA)
  • Software Systems (AREA)
  • Traffic Control Systems (AREA)

Abstract

The invention discloses a method and a device for matching traffic lights in an automatic driving scene, and relates to the technical field of automatic driving. The method comprises the following steps: calculating offset vectors of the projection points relative to all detection frames according to the detection frames of the traffic lights in the image and the projection points of the traffic lights in the high-definition map in the image; generating a plurality of matching schemes according to the offset vectors of the projection points; determining the connection line between the projection point and the detection frame in the same matching combination; calculating an image topological relation index according to the number of intersection points among connecting lines of different matching combinations; calculating outlier indexes according to the length difference between the connecting lines of different matching combinations; counting the number of the traffic lights obtained by detection; calculating a matching quantity index according to the quantity of the detected traffic lights; and screening the multiple matching schemes by using the evaluation indexes in turn according to the priority of the evaluation indexes to obtain a target matching scheme. According to the method and the device, the detection frame corresponding to the traffic light in the high-precision map can be accurately determined.

Description

Traffic light matching method and device in automatic driving scene
Technical Field
The invention relates to the technical field of automatic driving, in particular to a traffic light matching method and device in an automatic driving scene.
Background
In the field of automatic driving, traffic light detection is critical to vehicle travel. At present, the position of traffic lights needing to be focused on a lane where a current driving direction is located in the three-dimensional world is generally obtained based on a high-precision map, the projection points of the traffic lights in a two-dimensional image acquired by a camera are obtained after coordinate conversion, and the detection classification of the traffic lights is carried out based on the projection points, so that the state information of the traffic lights is obtained.
However, in the actual application scenario, the detection process may have conditions of missed detection, false detection and the like due to the influence of factors such as illumination change, traffic light shielding, traffic light fault, temporary shift of traffic lights and the like, so that the detection information obtained through the two-dimensional image is different from the traffic light information in the high-precision map, for example, the quantity is different or the positions are different. Therefore, the traffic light in the high-precision map needs to be matched with the detection frame, and the state of the traffic light is obtained.
Disclosure of Invention
In view of the above, the embodiment of the invention provides a method and a device for matching traffic lights in an automatic driving scene, which can accurately determine a detection frame corresponding to the traffic lights in a high-precision map.
In a first aspect, an embodiment of the present invention provides a method for matching traffic lights in an autopilot scenario, including:
calculating offset vectors of the projection points relative to all detection frames according to the detection frames of the traffic lights in the image and the projection points of the traffic lights in the high-precision map in the image;
generating a plurality of matching schemes according to the offset vectors of the projection points; any one of the matching schemes comprises: a plurality of matching combinations composed of projection points and detection frames;
for each of the matching schemes: determining the connection line between the projection point and the detection frame in the same matching combination; calculating an image topological relation index according to the number of intersection points among connecting lines of different matching combinations; calculating outlier indexes according to the length difference between the connecting lines of different matching combinations; counting the number of the traffic lights obtained by detection; calculating a matching quantity index according to the quantity of the detected traffic lights;
screening the multiple matching schemes by using the evaluation indexes in sequence according to the preset evaluation index priority to obtain a target matching scheme;
wherein the evaluation index includes: the image topological relation index, the outlier index and the matching quantity index; the image topological relation index is used for evaluating a matching scheme from the coordinate position dimension of the traffic light; the outlier index is used for evaluating a matching scheme from the distribution dimension of the traffic lights; and the matching quantity index is used for evaluating a matching scheme from the quantity dimension of the traffic lights.
In a second aspect, an embodiment of the present invention provides a device for matching traffic lights in an autopilot scene, including:
the generation module is configured to calculate offset vectors of the projection points relative to all detection frames according to the detection frames of the traffic lights in the image and the projection points of the traffic lights in the high-precision map in the image; generating a plurality of matching schemes according to the offset vectors of the projection points; any one of the matching schemes comprises: a plurality of matching combinations composed of projection points and detection frames;
a calculation module configured to, for each of the matching schemes: determining the connection line between the projection point and the detection frame in the same matching combination; calculating an image topological relation index according to the number of intersection points among connecting lines of different matching combinations; calculating outlier indexes according to the length difference between the connecting lines of different matching combinations; counting the number of the traffic lights obtained by detection; calculating a matching quantity index according to the quantity of the detected traffic lights;
the screening module is configured to screen the multiple matching schemes by sequentially using the evaluation indexes according to the preset evaluation index priority, so as to obtain a target matching scheme;
wherein the evaluation index includes: the image topological relation index, the outlier index and the matching quantity index; the image topological relation index is used for evaluating a matching scheme from the coordinate position dimension of the traffic light; the outlier index is used for evaluating a matching scheme from the distribution dimension of the traffic lights; and the matching quantity index is used for evaluating a matching scheme from the quantity dimension of the traffic lights.
One embodiment of the above invention has the following advantages or benefits: the projection point error caused by converting the world coordinate system into the two-dimensional coordinate system of the camera can be corrected by calculating the offset vector, so that the matching distance is more accurate. The image topological relation index can solve the problem of difficult matching caused by the fact that the detection frame is close to the projection point, the outlier index considers the influence of the detection frame obtained by false detection, the matching quantity index considers the quantity matching degree of the detection frame and the projection point. And screening the matching schemes according to the set evaluation index priority, and evaluating the matching schemes from three dimensions, so that the final target matching scheme can be screened out quickly and accurately.
Further effects of the above-described non-conventional alternatives are described below in connection with the embodiments.
Drawings
The drawings are included to provide a better understanding of the invention and are not to be construed as unduly limiting the invention. Wherein:
fig. 1 is a flowchart of a method for matching traffic lights in an autopilot scenario according to one embodiment of the present invention;
FIG. 2 is a diagram of two matching combinations without an intersection provided by one embodiment of the present invention;
FIG. 3 is a diagram of two matching combinations without an intersection provided by one embodiment of the present invention;
FIG. 4 is a height set provided by one embodiment of the present invention;
FIG. 5 is another set of heights provided by an embodiment of the present invention;
FIG. 6 is a diagram of two plane sets provided by one embodiment of the invention;
FIG. 7 is a schematic view of a traffic light projector according to one embodiment of the present invention;
fig. 8 is a schematic diagram of a traffic light matching device in an autopilot scenario according to an embodiment of the present invention;
fig. 9 is a schematic diagram of a computer system suitable for use in implementing an embodiment of the invention.
Detailed Description
Exemplary embodiments of the present invention will now be described with reference to the accompanying drawings, in which various details of the embodiments of the present invention are included to facilitate understanding, and are to be considered merely exemplary. Accordingly, those of ordinary skill in the art will recognize that various changes and modifications of the embodiments described herein can be made without departing from the scope and spirit of the invention. Also, descriptions of well-known functions and constructions are omitted in the following description for clarity and conciseness.
As shown in fig. 1, an embodiment of the present invention provides a method for matching traffic lights in an autopilot scene, including:
step 101: and calculating offset vectors of the projection points relative to all the detection frames according to the detection frames of the traffic lights in the image and the projection points of the traffic lights in the high-definition map in the image.
Although there may be a false detection or missing detection in the actual application scenario, considering that the detection is accurate, the number of detection frames and the number of projection points should be the same, in order to ensure the accuracy of the matching result, in the embodiment of the present invention, the number of detection frames and the number of projection points are the same.
Step 102: generating a plurality of matching schemes according to the offset vectors of the projection points; any matching scheme comprises the following steps: and a plurality of matching combinations formed by the projection points and the detection frames.
For the same projection point, the offset vectors relative to different detection frames respectively correspond to different matching schemes.
Step 103: for each matching scheme: determining the connection line between the projection point and the detection frame in the same matching combination; calculating an image topological relation index according to the number of intersection points among connecting lines of different matching combinations; calculating outlier indexes according to the length difference between the connecting lines of different matching combinations; counting the number of the traffic lights obtained by detection; and calculating a matching quantity index according to the quantity of the detected traffic lights.
Step 104: and screening the multiple matching schemes by using the evaluation indexes in sequence according to the preset priority of the evaluation indexes to obtain a target matching scheme.
Wherein, the evaluation index includes: an image topological relation index, an outlier index and a matching quantity index; the image topological relation index is used for evaluating a matching scheme from the coordinate position dimension of the traffic light; the outlier index is used for evaluating a matching scheme from the distribution dimension of the traffic lights; and the matching quantity index is used for evaluating the matching scheme from the quantity dimension of the traffic lights.
For example, there are 16 matching schemes, 10 matching schemes are selected based on the image topological relation index, 6 matching schemes are selected from 10 matching schemes based on the outlier index, and 1 matching scheme is selected from 6 matching schemes based on the matching quantity index. The priority of the evaluation index can be adjusted according to the requirements of the actual scene.
The projection point error caused by converting the world coordinate system into the two-dimensional coordinate system of the camera can be corrected by calculating the offset vector, so that the matching distance is more accurate. The image topological relation index can solve the problem of difficult matching caused by the fact that the detection frame is close to the projection point, the outlier index considers the influence of the detection frame obtained by false detection, the matching quantity index considers the quantity matching degree of the detection frame and the projection point. And screening the matching schemes according to the set evaluation index priority, and evaluating the matching schemes from three dimensions, so that the final target matching scheme can be screened out quickly and accurately.
In one embodiment of the present invention, calculating an offset vector of a projection point with respect to each detection frame according to a detection frame of a plurality of traffic lights in an image and a projection point of a plurality of traffic lights in a high-definition map in the image includes:
for each projection point of the traffic lights in the high-definition map in the image, the following steps are executed: and calculating the offset vector of the projection point relative to each detection frame according to the coordinates of the projection point and the coordinates of the center of each detection frame.
For example, the detection frames are A, B and C, the projection points are F, G and H, and for the projection point F, the offset vectors of F with respect to A, B and C are calculated, respectively, and the F coordinate is (F 1 ,f 2 ) The A coordinate is (a 1 ,a 2 ) The offset vector is
The embodiment of the invention can accurately measure the position deviation of the detection frame and the projection point through the offset vector, and improve the accuracy of the matching result.
In one embodiment of the present invention, generating a plurality of matching schemes according to offset vectors of respective projection points includes:
calculating the offset distance of the projection point relative to each detection frame according to the offset vector of the projection point relative to each detection frame;
and carrying out bipartite graph matching according to the offset distance of each projection point to obtain a plurality of matching schemes.
Along the line of the above example of use,is +.>
Preferably, bipartite graph matching may employ hungarian algorithm or the like. According to the embodiment of the invention, the bipartite graph matching is adopted to match the projection points with the detection frame, so that the accuracy of a matching result is improved.
In one embodiment of the present invention, calculating an image topology index according to the number of intersections between the lines of different matching combinations includes:
counting the number of intersection points among connecting lines of each matching combination in the matching scheme;
dividing the matching combination in the matching scheme into a plurality of height groups based on the z value of the traffic light of the projection point in the high-precision map, and respectively counting the number of intersection points between connecting lines of different matching combinations in each height group;
dividing each height group into a plurality of plane groups based on an x value and a y value of a traffic light of which the projection point belongs in a high-precision map, and respectively counting the number of intersection points between connecting lines of different matching combinations in each plane group;
and calculating an image topological relation index according to the number of the intersections between the connecting lines of the matching combinations in the matching scheme, the number of the intersections between the connecting lines of the different matching combinations in the height groups and the number of the intersections between the connecting lines of the different matching combinations in the plane groups.
The image topological relation index can be the sum of the number of intersection points between the connecting lines of each matching combination in the matching scheme, the number of intersection points between the connecting lines of different matching combinations in each height group and the number of intersection points between the connecting lines of different matching combinations in each plane group, and the matching scheme with a small number of intersection points is preferably selected.
The traffic lights are installed in a specified height range, the longitudinal distribution is not greatly different, and the transverse distribution of the traffic lights is related to the size of the intersection. The traffic lights in the high-precision map are arranged from left to right, so the sequence of the detection frames on the matching should also be from left to right, if it is not reasonable to match the traffic lights on the left side of the map to the detection frames on the right side. Based on this, in the embodiment of the present invention, the number of intersections between the connection lines of each matching combination in the matching scheme is counted, as shown in fig. 2, the detection frames and the projection points in the two matching combinations are respectively connected, and no intersection exists between the two lines, as shown in fig. 3.
In some scenarios, the connection lines of the two matching combinations have an intersection point, but the installation heights of the two corresponding traffic lights are different, and in essence, the two matching combinations are correct. In order to prevent the above situation, the embodiment of the present invention further divides the matching combination in the matching scheme into a plurality of height groups based on the z value of the traffic light to which the projection point belongs in the high-precision map, for example, fig. 4 and 5 are two height groups.
In some scenarios, traffic lights at the same height but at different locations will overlap in the image, resulting in intersections between links, but essentially matching combinations are correct. Based on this, the embodiment of the present invention divides each height group into a plurality of plane groups based on the x value and the y value of the traffic light to which the projection point belongs in the high-precision map, as shown in fig. 6, into two plane groups of far and near.
As shown in fig. 7, there are 5 traffic lights in front of the vehicle, and the traffic lights are projected into an image and then divided into three groups for processing.
The embodiment of the invention can improve the accuracy of the image topological relation index by grouping and counting the number of the intersection points, so that the matching relation between the detection frame and the projection points can be accurately reflected.
In one embodiment of the present invention, calculating an outlier index based on a length difference between links of different matching combinations includes:
determining the number of target matching combinations in a matching scheme according to the length of the connecting lines of the matching combinations; the ratio of the length of the connecting line of the target matching combination to the length of the connecting line of each other matching combination is within a preset ratio range;
and calculating an outlier index according to the number of target matching combinations in the matching scheme.
Considering that the conditions of missed detection and false detection exist, the detection frame may be matched with the wrong projection point, so that the detection frame is different from other correct connection line lengths, namely an outlier. The fewer and better the outliers in the matching scheme, in the embodiment of the present invention, the length of the connection line of the target matching combination is the outlier. For example, the ratio of the length of the connection line of the matching combination 1 to the length of the connection line of the other matching combinations is greater than 1.3, and the matching combination 1 is the target matching combination. The outlier indicator may be the number of target match combinations in the matching scheme, with a preference for a matching scheme with a fewer number of target match combinations.
In one embodiment of the present invention, calculating the matching number index according to the number of detected traffic lights includes:
determining the number of the front Jing Gong green lights in the traffic lights corresponding to the matching scheme; the included angle between the connecting line of the vehicle and the front Jing Gong green light and the direction of the front Jing Gong green light is smaller than a preset angle threshold, the distance between the front Jing Gong green light and the vehicle is not greater than the distance between the vehicle and the target traffic light, and the target traffic light is the traffic light which is positioned in front of the lane where the vehicle is positioned and closest to the vehicle;
and calculating a matching quantity index according to the quantity of the green lights of the front Jing Gong.
According to the embodiment of the invention, traffic lights which need to be focused on a lane where the own vehicle is located can be considered preferentially, and the running safety of the own vehicle is ensured.
In one embodiment of the invention, calculating the matching number index according to the number of the first Jing Gong green lights comprises:
based on the detection frame, counting the sum of the numbers of red lights, yellow lights and green lights in the image recognition result;
and calculating a matching quantity index based on the quantity of the Jing Gong green lights before the sum of the quantity of the red lights, the yellow lights and the green lights.
The matching number index may be the sum of the numbers of the front Jing Gong green, red, yellow and green lights. The difference between the sum of the projection points and the sum of the red light, the yellow light and the green light comprises a black traffic light as a recognition result, and can also comprise a traffic light which is not recognized to be matched and the like. The matching scheme with a greater sum of the numbers of green, red, yellow and green lights before Jing Gong is preferred. Of course, other ways of calculating the above three indexes are also possible, for example, calculating the matching number index based on the number of green lights of the first Jing Gong only.
As shown in fig. 8, an embodiment of the present invention provides a device for matching traffic lights in an autopilot scene, including:
the generating module 801 is configured to calculate offset vectors of the projection points relative to each detection frame according to the detection frames of the plurality of traffic lights in the image and the projection points of the plurality of traffic lights in the high-precision map in the image; generating a plurality of matching schemes according to the offset vectors of the projection points; any matching scheme comprises the following steps: a plurality of matching combinations composed of projection points and detection frames;
a calculation module 802 configured to, for each matching scheme: determining the connection line between the projection point and the detection frame in the same matching combination; calculating an image topological relation index according to the number of intersection points among connecting lines of different matching combinations; calculating outlier indexes according to the length difference between the connecting lines of different matching combinations; counting the number of the traffic lights obtained by detection; calculating a matching quantity index according to the quantity of the detected traffic lights;
the screening module 803 is configured to sequentially screen the multiple matching schemes by using the evaluation indexes according to the preset evaluation index priority, so as to obtain a target matching scheme;
wherein, the evaluation index includes: an image topological relation index, an outlier index and a matching quantity index; the image topological relation index is used for evaluating a matching scheme from the coordinate position dimension of the traffic light; the outlier index is used for evaluating a matching scheme from the distribution dimension of the traffic lights; and the matching quantity index is used for evaluating the matching scheme from the quantity dimension of the traffic lights.
In one embodiment of the present invention, the generating module 801 is configured to perform, for each projection point of each traffic light in the high-precision map in the image: and calculating the offset vector of the projection point relative to each detection frame according to the coordinates of the projection point and the coordinates of the center of each detection frame.
In one embodiment of the present invention, the generating module 801 is configured to calculate an offset distance of the projection point with respect to each detection frame according to an offset vector of the projection point with respect to each detection frame; and carrying out bipartite graph matching according to the offset distance of each projection point to obtain a plurality of matching schemes.
In one embodiment of the present invention, the calculation module 802 is configured to count the number of intersections between the lines of each matching combination in the matching scheme; dividing the matching combination in the matching scheme into a plurality of height groups based on the z value of the traffic light of the projection point in the high-precision map, and respectively counting the number of intersection points between connecting lines of different matching combinations in each height group; dividing each height group into a plurality of plane groups based on an x value and a y value of a traffic light of which the projection point belongs in a high-precision map, and respectively counting the number of intersection points between connecting lines of different matching combinations in each plane group; and calculating an image topological relation index according to the number of the intersections between the connecting lines of the matching combinations in the matching scheme, the number of the intersections between the connecting lines of the different matching combinations in the height groups and the number of the intersections between the connecting lines of the different matching combinations in the plane groups.
In one embodiment of the present invention, the calculation module 802 is configured to determine the number of target matching combinations in the matching scheme according to the length of the connection line of the matching combinations; the ratio of the length of the connecting line of the target matching combination to the length of the connecting line of each other matching combination is within a preset ratio range; and calculating an outlier index according to the number of target matching combinations in the matching scheme.
In one embodiment of the present invention, the calculating module 802 is configured to determine the number of the first Jing Gong green lights in the traffic lights corresponding to the matching scheme; calculating a matching quantity index according to the quantity of the green lights of the front Jing Gong; the included angle between the connecting line of the vehicle and the front Jing Gong green light and the direction of the front Jing Gong green light is smaller than a preset angle threshold, the distance between the front Jing Gong green light and the vehicle is not greater than the distance between the vehicle and the target traffic light, and the target traffic light is the traffic light which is positioned in front of the lane where the vehicle is positioned and closest to the vehicle.
In one embodiment of the present invention, the calculation module 802 is configured to count the sum of the numbers of red lights, yellow lights and green lights in the image recognition result based on the detection frame; and calculating a matching quantity index based on the quantity of the Jing Gong green lights before the sum of the quantity of the red lights, the yellow lights and the green lights.
The embodiment of the invention provides electronic equipment, which comprises:
one or more processors;
storage means for storing one or more programs,
the one or more programs, when executed by the one or more processors, cause the one or more processors to implement the method of any of the embodiments described above.
The present invention provides a computer readable medium having stored thereon a computer program which when executed by a processor implements a method as in any of the embodiments described above.
Referring now to FIG. 9, there is illustrated a schematic diagram of a computer system 900 suitable for use in implementing an embodiment of the present invention. The terminal device shown in fig. 9 is only an example, and should not impose any limitation on the functions and the scope of use of the embodiment of the present invention.
As shown in fig. 9, the computer system 900 includes a Central Processing Unit (CPU) 901, which can execute various appropriate actions and processes according to a program stored in a Read Only Memory (ROM) 902 or a program loaded from a storage section 908 into a Random Access Memory (RAM) 903. In the RAM 903, various programs and data necessary for the operation of the system 900 are also stored. The CPU 901, ROM 902, and RAM 903 are connected to each other through a bus 904. An input/output (I/O) interface 905 is also connected to the bus 904.
The following components are connected to the I/O interface 905: an input section 906 including a keyboard, a mouse, and the like; an output portion 907 including a display such as a Cathode Ray Tube (CRT), a Liquid Crystal Display (LCD), and a speaker; a storage portion 908 including a hard disk or the like; and a communication section 909 including a network interface card such as a LAN card, a modem, or the like. The communication section 909 performs communication processing via a network such as the internet. The drive 910 is also connected to the I/O interface 905 as needed. A removable medium 911 such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, or the like is installed as needed on the drive 910 so that a computer program read out therefrom is installed into the storage section 908 as needed.
In particular, according to embodiments of the present disclosure, the processes described above with reference to flowcharts may be implemented as computer software programs. For example, embodiments of the present disclosure include a computer program product comprising a computer program embodied on a computer readable medium, the computer program comprising program code for performing the method shown in the flow chart. In such an embodiment, the computer program may be downloaded and installed from the network via the communication portion 909 and/or installed from the removable medium 911. The above-described functions defined in the system of the present invention are performed when the computer program is executed by a Central Processing Unit (CPU) 901.
The computer readable medium shown in the present invention may be a computer readable signal medium or a computer readable storage medium, or any combination of the two. The computer readable storage medium can be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or a combination of any of the foregoing. More specific examples of the computer-readable storage medium may include, but are not limited to: an electrical connection having 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 portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In the context of this document, a computer readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. In the present invention, however, the computer-readable signal medium may include a data signal propagated in baseband or as part of a carrier wave, with the computer-readable program code embodied therein. Such a propagated data signal may take any of a variety of forms, including, but not limited to, electro-magnetic, optical, or any suitable combination of the foregoing. A computer readable signal medium may also be any computer readable medium that is not a computer readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device. Program code embodied on a computer readable medium may be transmitted using any appropriate medium, including but not limited to: wireless, wire, fiber optic cable, RF, etc., or any suitable combination of the foregoing.
The flowcharts and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to various embodiments of the present invention. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that, in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams or flowchart illustration, and combinations of blocks in the block diagrams or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.
The modules involved in the embodiments of the present invention may be implemented in software or in hardware. The described modules may also be provided in a processor, for example, as: a processor includes a sending module, an obtaining module, a determining module, and a first processing module. The names of these modules do not in some cases limit the module itself, and for example, the transmitting module may also be described as "a module that transmits a picture acquisition request to a connected server".
The above embodiments do not limit the scope of the present invention. It will be apparent to those skilled in the art that various modifications, combinations, sub-combinations and alternatives can occur depending upon design requirements and other factors. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present invention should be included in the scope of the present invention.

Claims (10)

1. The method for matching the traffic lights in the automatic driving scene is characterized by comprising the following steps of:
calculating offset vectors of the projection points relative to all detection frames according to the detection frames of the traffic lights in the image and the projection points of the traffic lights in the high-precision map in the image;
generating a plurality of matching schemes according to the offset vectors of the projection points; any one of the matching schemes comprises: a plurality of matching combinations composed of projection points and detection frames;
for each of the matching schemes: determining the connection line between the projection point and the detection frame in the same matching combination; calculating an image topological relation index according to the number of intersection points among connecting lines of different matching combinations; calculating outlier indexes according to the length difference between the connecting lines of different matching combinations; counting the number of the traffic lights obtained by detection; calculating a matching quantity index according to the quantity of the detected traffic lights;
screening the multiple matching schemes by using the evaluation indexes in sequence according to the preset evaluation index priority to obtain a target matching scheme;
wherein the evaluation index includes: the image topological relation index, the outlier index and the matching quantity index; the image topological relation index is used for evaluating a matching scheme from the coordinate position dimension of the traffic light; the outlier index is used for evaluating a matching scheme from the distribution dimension of the traffic lights; and the matching quantity index is used for evaluating a matching scheme from the quantity dimension of the traffic lights.
2. The method of claim 1, wherein,
according to the detection frames of a plurality of traffic lights in an image and projection points of a plurality of traffic lights in a high-precision map in the image, calculating offset vectors of the projection points relative to the detection frames, wherein the offset vectors comprise:
for each projection point of the traffic lights in the high-definition map in the image, the following steps are executed: and calculating the offset vector of the projection point relative to each detection frame according to the coordinates of the projection point and the coordinates of the center of each detection frame.
3. The method of claim 1, wherein,
generating multiple matching schemes according to the offset vector of each projection point, wherein the matching schemes comprise:
calculating the offset distance of the projection point relative to each detection frame according to the offset vector of the projection point relative to each detection frame;
and carrying out bipartite graph matching according to the offset distance of each projection point to obtain a plurality of matching schemes.
4. The method of claim 1, wherein,
calculating an image topological relation index according to the number of intersection points among connecting lines of different matching combinations, wherein the method comprises the following steps:
counting the number of intersection points among connecting lines of each matching combination in the matching scheme;
dividing the matching combination in the matching scheme into a plurality of height groups based on the z value of the traffic light of the projection point in the high-precision map, and respectively counting the number of intersection points between connecting lines of different matching combinations in each height group;
dividing each height group into a plurality of plane groups based on an x value and a y value of a traffic light of which the projection point belongs in a high-precision map, and respectively counting the number of intersection points between connecting lines of different matching combinations in each plane group;
and calculating the image topological relation index according to the number of the intersection points among the connecting lines of the matching combinations in the matching scheme, the number of the intersection points among the connecting lines of the different matching combinations in the height groups and the number of the intersection points among the connecting lines of the different matching combinations in the plane groups.
5. The method of claim 1, wherein,
calculating outlier indexes according to the length difference between connecting lines of different matching combinations, wherein the outlier indexes comprise:
determining the number of target matching combinations in the matching scheme according to the length of the connecting lines of the matching combinations; the ratio of the length of the connecting line of the target matching combination to the length of the connecting line of each other matching combination is within a preset ratio range;
and calculating the outlier index according to the number of target matching combinations in the matching scheme.
6. The method of claim 1, wherein,
according to the number of the detected traffic lights, calculating a matching number index, including:
determining the number of the front Jing Gong green lights in the traffic lights corresponding to the matching scheme; the included angle between the connecting line of the vehicle and the front Jing Gong green light and the direction of the front Jing Gong green light is smaller than a preset angle threshold, the distance between the front Jing Gong green light and the vehicle is not larger than the distance between the vehicle and a target traffic light, and the target traffic light is a traffic light positioned in front of a lane where the vehicle is positioned and closest to the vehicle;
and calculating the matching quantity index according to the quantity of the front Jing Gong green lights.
7. The method of claim 6, wherein,
calculating the matching number index according to the number of the front Jing Gong green lights, including:
based on the detection frame, counting the sum of the numbers of red lights, yellow lights and green lights in the image recognition result;
and calculating the matching quantity index based on the sum of the quantity of red lights, yellow lights and green lights and the quantity of the front Jing Gong green lights.
8. A traffic light matching device in an autopilot scene, comprising:
the generation module is configured to calculate offset vectors of the projection points relative to all detection frames according to the detection frames of the traffic lights in the image and the projection points of the traffic lights in the high-precision map in the image; generating a plurality of matching schemes according to the offset vectors of the projection points; any one of the matching schemes comprises: a plurality of matching combinations composed of projection points and detection frames;
a calculation module configured to, for each of the matching schemes: determining the connection line between the projection point and the detection frame in the same matching combination; calculating an image topological relation index according to the number of intersection points among connecting lines of different matching combinations; calculating outlier indexes according to the length difference between the connecting lines of different matching combinations; counting the number of the traffic lights obtained by detection; calculating a matching quantity index according to the quantity of the detected traffic lights;
the screening module is configured to screen the multiple matching schemes by sequentially using the evaluation indexes according to the preset evaluation index priority, so as to obtain a target matching scheme;
wherein the evaluation index includes: the image topological relation index, the outlier index and the matching quantity index; the image topological relation index is used for evaluating a matching scheme from the coordinate position dimension of the traffic light; the outlier index is used for evaluating a matching scheme from the distribution dimension of the traffic lights; and the matching quantity index is used for evaluating a matching scheme from the quantity dimension of the traffic lights.
9. An electronic device, comprising:
one or more processors;
storage means for storing one or more programs,
when executed by the one or more processors, causes the one or more processors to implement the method of any of claims 1-7.
10. A computer readable medium, on which a computer program is stored, characterized in that the program, when being executed by a processor, implements the method according to any of claims 1-7.
CN202311078689.5A 2023-08-25 2023-08-25 Traffic light matching method and device in automatic driving scene Pending CN117095381A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202311078689.5A CN117095381A (en) 2023-08-25 2023-08-25 Traffic light matching method and device in automatic driving scene

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202311078689.5A CN117095381A (en) 2023-08-25 2023-08-25 Traffic light matching method and device in automatic driving scene

Publications (1)

Publication Number Publication Date
CN117095381A true CN117095381A (en) 2023-11-21

Family

ID=88774956

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202311078689.5A Pending CN117095381A (en) 2023-08-25 2023-08-25 Traffic light matching method and device in automatic driving scene

Country Status (1)

Country Link
CN (1) CN117095381A (en)

Similar Documents

Publication Publication Date Title
CN113607185B (en) Lane line information display method, lane line information display device, electronic device, and computer-readable medium
CN111950543A (en) Target detection method and device
US10783373B2 (en) Method and apparatus for augmenting reality
CN114863380B (en) Lane line identification method and device and electronic equipment
CN115641359B (en) Method, device, electronic equipment and medium for determining movement track of object
CN114612616A (en) Mapping method and device, electronic equipment and storage medium
KR20160131222A (en) Method and apparatus for vehicle position recognizing and route searching through video analysis
WO2024007869A1 (en) Levelness verification method, terminal, and computer-readable storage medium
CN115620264B (en) Vehicle positioning method and device, electronic equipment and computer readable medium
CN117095381A (en) Traffic light matching method and device in automatic driving scene
CN114611635B (en) Object identification method and device, storage medium and electronic device
CN113780247B (en) Traffic light detection method and device, electronic equipment and computer readable medium
CN113538556B (en) Volume measuring device based on IR diagram
CN115018926A (en) Method, device and equipment for determining pitch angle of vehicle-mounted camera and storage medium
CN110634159A (en) Target detection method and device
CN114550116A (en) Object identification method and device
CN113781569A (en) Loop detection method and device
CN113112551A (en) Camera parameter determination method and device, road side equipment and cloud control platform
CN112597788A (en) Target measuring method, target measuring device, electronic apparatus, and computer-readable medium
CN115359227B (en) Fusion method and device of regional live-action map and lane-level map and electronic equipment
CN115147789B (en) Method, device, equipment and computer readable medium for detecting split and combined road information
CN116630436B (en) Camera external parameter correction method, camera external parameter correction device, electronic equipment and computer readable medium
CN114049615B (en) Traffic object fusion association method and device in driving environment and edge computing equipment
CN115409888B (en) Intelligent positioning method and device for pole tower in inspection of distribution network unmanned aerial vehicle
CN114219907B (en) Three-dimensional map generation 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