CN114842452A - Traffic signal lamp identification method, device and equipment for automatic driving - Google Patents
Traffic signal lamp identification method, device and equipment for automatic driving Download PDFInfo
- Publication number
- CN114842452A CN114842452A CN202210629737.4A CN202210629737A CN114842452A CN 114842452 A CN114842452 A CN 114842452A CN 202210629737 A CN202210629737 A CN 202210629737A CN 114842452 A CN114842452 A CN 114842452A
- Authority
- CN
- China
- Prior art keywords
- traffic signal
- target
- signal lamp
- image
- data
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- 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
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/25—Determination of region of interest [ROI] or a volume of interest [VOI]
-
- 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
- G06V10/77—Processing image or video features in feature spaces; using data integration or data reduction, e.g. principal component analysis [PCA] or independent component analysis [ICA] or self-organising maps [SOM]; Blind source separation
- G06V10/774—Generating sets of training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V2201/00—Indexing scheme relating to image or video recognition or understanding
- G06V2201/07—Target detection
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Software Systems (AREA)
- Computing Systems (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Computation (AREA)
- Medical Informatics (AREA)
- Databases & Information Systems (AREA)
- General Health & Medical Sciences (AREA)
- Health & Medical Sciences (AREA)
- Data Mining & Analysis (AREA)
- General Engineering & Computer Science (AREA)
- Mathematical Physics (AREA)
- Traffic Control Systems (AREA)
Abstract
The application discloses a traffic signal lamp identification method and device for automatic driving, electronic equipment and storage media, wherein the method is used for automatically driving a vehicle and comprises the following steps: acquiring image information; obtaining a detection result in the image information through a pre-trained target detection model, wherein the target detection model is obtained by using multiple groups of data through machine learning training, and each group of data in the multiple groups of data comprises: image data and a tag in the image data; and obtaining the identification result of the traffic signal lamp according to the detection result of the first frame image and the two target frames in the detection result of the second frame image in the image information, wherein the two target frames comprise the same target traffic signal lamp. By the method and the device, real-time traffic signal lamp information can be acquired, and the size of the traffic signal lamp does not influence the identification result.
Description
Technical Field
The present disclosure relates to the field of automatic driving technologies, and in particular, to a method and an apparatus for identifying traffic lights for automatic driving, an electronic device, and a storage medium.
Background
When the automatic driving vehicle runs to the intersection close to the traffic signal lamp, the distance from the vehicle to the traffic signal lamp and the height of the traffic signal lamp can be accurately obtained, and the automatic driving method has important significance for automatic driving. The distance of the traffic light is obtained, and support can be provided for an automatic driving vehicle to make a correct strategy in the aspect of speed control; the height of the traffic signal lamp is obtained, so that the automatic driving vehicle and the front vehicle can keep a proper distance, and when the front vehicle is a tall bus or a large truck, the automatic driving vehicle and the front vehicle are too close to each other, the traffic signal lamp can be shielded, and the traffic signal lamp cannot be identified.
In the related art, information such as the coordinate position, the size of the size, the height and the like of a traffic signal lamp is recorded in a pre-made off-line high-precision map, so that the height of the traffic signal lamp in front and the distance between the traffic signal lamp and a vehicle can be obtained through the high-precision map and the vehicle positioning information.
However, the high-precision map and the positioning information have errors and even fail, and it cannot be guaranteed that the high-precision map can always reflect the latest traffic light information, that is, the traffic light information in the high-precision map may be out of date.
Disclosure of Invention
The embodiment of the application provides a traffic signal lamp identification method and device for automatic driving, electronic equipment and a storage medium, so that information of a traffic signal lamp can be accurately acquired in real time.
The embodiment of the application adopts the following technical scheme:
in a first aspect, an embodiment of the present application provides a traffic signal light recognition method for automatic driving, where, for an automatic driving vehicle, the method includes: acquiring image information; obtaining a detection result in the image information through a pre-trained target detection model, wherein the target detection model is obtained by using multiple groups of data through machine learning training, and each group of data in the multiple groups of data comprises: image data and a tag in the image data; and obtaining the identification result of the traffic signal lamp according to the detection result of the first frame image and the two target frames in the detection result of the second frame image in the image information, wherein the two target frames comprise the same target traffic signal lamp.
In a second aspect, an embodiment of the present application further provides a traffic signal light recognition device for automatic driving, where the device includes: the acquisition module is used for acquiring image information; the detection module is used for obtaining a detection result in the image information through a pre-trained target detection model, wherein the target detection model is obtained by using multiple groups of data through machine learning training, and each group of data in the multiple groups of data comprises: image data and a tag in the image data; and the identification module is used for obtaining the identification result of the traffic signal lamp according to the detection result of the first frame image and the two target frames in the detection result of the second frame image in the image information, wherein the two target frames comprise the same target traffic signal lamp.
In a third aspect, an embodiment of the present application further provides an electronic device, including: a processor; and a memory arranged to store computer executable instructions that, when executed, cause the processor to perform the above method.
In a fourth aspect, embodiments of the present application also provide a computer-readable storage medium storing one or more programs that, when executed by an electronic device including a plurality of application programs, cause the electronic device to perform the above-described method.
The embodiment of the application adopts at least one technical scheme which can achieve the following beneficial effects:
firstly, a detection result in image information is obtained through a pre-trained target detection model, and then the distance between a traffic signal lamp and a current vehicle and the height of the traffic signal lamp are obtained according to the detection result of a first frame image and two target frames in the detection result of a second frame image in the image information. The method and the device do not depend on the size of the traffic signal lamp to be identified, and the condition that the vehicle positioning information is inaccurate under the condition that high-precision map data is invalid is avoided.
Drawings
The accompanying drawings, which are included to provide a further understanding of the application and are incorporated in and constitute a part of this application, illustrate embodiment(s) of the application and together with the description serve to explain the application and not to limit the application. In the drawings:
FIG. 1 is a schematic flow chart of a traffic light recognition method for automatic driving according to an embodiment of the present disclosure;
FIG. 2 is a schematic structural diagram of a traffic light recognition device for automatic driving according to an embodiment of the present application;
FIG. 3 is a schematic diagram illustrating a geometric relationship between a host vehicle and a traffic light at a first time in the traffic light recognition method for automatic driving according to the embodiment of the present application;
FIG. 4 is a schematic view illustrating a geometric relationship between a host vehicle and a traffic light at a second time in the traffic light recognition method for automatic driving according to the embodiment of the present application;
fig. 5 is a schematic structural diagram of an electronic device in an embodiment of the present application.
Detailed Description
In order to make the objects, technical solutions and advantages of the present application more apparent, the technical solutions of the present application will be described in detail and completely with reference to the following specific embodiments of the present application and the accompanying drawings. It should be apparent that the described embodiments are only some of the embodiments of the present application, 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 application.
The method in the embodiment of the application uses the traffic light target detection results of two frames of images at different moments, and utilizes the pinhole imaging and the similar triangle principle to realize the measurement of the distance and the height of the traffic light in front, thereby not only avoiding the problem of overdue or invalidation possibly existing in a high-precision map and the problem of inaccurate positioning information, but also avoiding the problem of inaccurate positioning information due to the adoption of a geometric calculation method which is independent of the size of the traffic light, and being suitable for the traffic light with any size.
The technical solutions provided by the embodiments of the present application are described in detail below with reference to the accompanying drawings.
The embodiment of the present application provides a traffic light identification method for automatic driving, and as shown in fig. 1, provides a schematic flow chart of the traffic light identification method for automatic driving in the embodiment of the present application, where the method at least includes the following steps S110 to S130:
in step S110, image information is acquired.
And acquiring image information by using a front camera in the automatic driving vehicle. Namely, the camera is used for shooting the front situation in real time in the running process of the automatic driving vehicle. Real-time processing is required for the image information and relevant recognition results are provided.
Step S120, obtaining a detection result in the image information through a pre-trained target detection model, wherein the target detection model is obtained by using multiple groups of data through machine learning training, and each group of data in the multiple groups of data comprises: image data and a label in the image data.
Usually, an off-line method is adopted to obtain a target detection model through pre-training. The target detection model is obtained by using a plurality of groups of data through machine learning training, and each group of data in the plurality of groups of data comprises: it can be understood that each image data has corresponding label information in its image information.
Preferably, the detection result of the traffic signal lamp in the image information is obtained through a previously trained YoloV5 target detection model.
Specifically, a traffic light detection model is trained by using a yoolov 5 model, so that a traffic light in an image can be detected, and the coordinates and the size (x) of the center point of a target frame can be output c ，y c ，w 2d ，h 2d ) Center point coordinate (x) of the target frame c ，y c ) Width and height dimensions (w) of the target frame 2d ，h 2d ) And the coordinate of the central point of the output target frame and the size of the output target frame can be used for calculating the target frame in the image informationLongitudinal (lateral fixation) down-edge position of (c): y is bottom ＝y c +h 2d /2。
Step S130, obtaining an identification result of the traffic signal lamp according to two target frames in the detection result of the first frame image and the detection result of the second frame image in the image information, where the two target frames both include one same target traffic signal lamp.
According to one target frame (usually, only one target frame can be determined when a plurality of target frames exist) in the detection result of the first frame image (which is selected randomly) in the image information, such as the area of the target frame is the largest), and according to the target frame (usually, only one target frame can be determined when a plurality of target frames exist, such as the area of the target frame is the largest) in the detection result of the second frame image in the image information, the geometric relationship is calculated through the two target frames obtained from the first frame image and the second frame image, and then the identification result of the traffic signal lamp can be obtained.
It should be noted that both of the object frames include an identical object traffic light, that is, both of the object frames include a unique and identical object traffic light.
Preferably, the identification result of the traffic light includes the distance from the traffic light to the current vehicle and the height of the traffic light. That is, the relative distance between the traffic signal and the self-vehicle in the recognition result can provide support for making a correct strategy for the speed control of the automatic driving vehicle by means of pure vision and geometric calculation. And the height of the traffic signal lamp in the identification result can keep the automatic driving vehicle at a proper distance from the front vehicle.
In one embodiment of the present application, the method further comprises: under the condition that the pre-loaded high-precision map data is invalid, obtaining the distance between the traffic signal lamp and the current vehicle and the height of the traffic signal lamp in the identification result of the traffic signal lamp; and/or under the condition that the size of the traffic signal lamp is unknown, obtaining the distance between the traffic signal lamp and the current vehicle and the height of the traffic signal lamp in the identification result of the traffic signal lamp.
In specific implementation, if the preloaded high-precision map data is invalid, such as the high-precision map data is expired and the SLAM positioning information is inaccurate, the distance from the traffic signal lamp to the current vehicle and the height of the traffic signal lamp in the identification result of the traffic signal lamp can be obtained through the method in the embodiment of the application, so that support is provided for automatic driving to keep a proper distance with the front vehicle.
Further, if the size of the traffic light is unknown (for example, for an urban traffic light in an unknown city), the distance from the traffic light to the current vehicle and the height of the traffic light in the recognition result of the traffic light can still be obtained by the method in the embodiment of the present application, so as to provide support for automatic driving or maintain a proper distance from the preceding vehicle.
In an embodiment of the present application, the detection result in the image information is obtained through a pre-trained target detection model, where the target detection model is obtained through machine learning training using multiple sets of data, and each set of data in the multiple sets of data includes: a sample image and the sample image label comprising: obtaining the position coordinates of a target frame of a traffic signal lamp in the image information and the size of the target frame through a pre-trained target detection model; and obtaining longitudinal and lower edge position information of the target frame in the image information according to the position coordinates of the target frame of the traffic signal lamp and the size of the target frame.
In specific implementation, for the target detection model, the position coordinates of the target frame of the traffic signal lamp in the image information and the size of the target frame can be obtained by detecting the traffic signal identifier in the image information after pre-training. And then, according to the position coordinates of the target frame of the traffic signal lamp and the size of the target frame, obtaining the longitudinal and lower edge position information of the target frame in the image information. For example,
output targetCoordinates of center point and size (x) of frame c ，y c ，w 2d ，h 2d ) And the down-edge position of the target frame in the longitudinal direction (fixed in the transverse direction) in the image information can be calculated according to the coordinates and the size of the center point of the output target frame: y is bottom ＝y c +h 2d /2。
In an embodiment of the present application, the obtaining, according to two target frames in the detection results of the first frame image and the second frame image in the image information, a recognition result of a traffic signal lamp, where the two target frames include a same target traffic signal lamp, includes: determining a first frame image corresponding to the first moment and a second frame image corresponding to a second moment, wherein the second moment is greater than the first moment and meets the requirement of the distance between the corresponding moment and the vehicle, and the first moment is selected arbitrarily; and obtaining the identification result of the traffic signal lamp according to the target frame in the detection result of the first frame image and the target frame in the detection result of the second frame image in the image information and a preset geometric processing method.
In specific implementation, when selecting an image frame, by determining a first frame image corresponding to the first time and a second frame image corresponding to the second time, it should be noted that the second time is greater than the first time and both meet the requirement of the distance between the corresponding time and the vehicle itself, and the first time is arbitrarily selected. For example, a proper first time and a proper second time are selected, so that the distance difference value corresponding to the two times is larger than or equal to a threshold value, and the distance difference value corresponding to the two times, namely the advancing distance of the self-vehicle, is known.
And further, obtaining an identification result of the traffic signal lamp according to a target frame in the detection result of the first frame image and a target frame in the detection result of the second frame image in the image information and a preset geometric processing method. It should be noted that the target frame in the detection result may include a plurality of target frames, and a most suitable one needs to be selected as the target frame. For example, according to the principle of how large and small the image is, the largest one of all the traffic signal target frames detected at the first time t1 is selected. Similarly, the one having the largest area is also selected at the second time t 2. The two target frames are considered to represent the same traffic light and are the target frames which are closest to the vehicle at the respective moments.
As shown in fig. 3 and 4, in an embodiment of the present application, the obtaining the recognition result of the traffic signal lamp according to the target frame in the detection result of the first frame image and the target frame in the detection result of the second frame image in the image information and a preset geometric processing method includes:
and determining a distance difference parameter according to the forward distance corresponding to the first moment and the forward distance corresponding to the second moment.
Firstly, obtaining a distance parameter z equal to z2-z1 in advance, and taking appropriate t1 and t2 to enable the value of z to be larger than or equal to 10 meters in order to avoid the situation that the error of the calculation result is large because the traveling distance of the vehicle between the time t1 and the time t2 is too short, and certainly, the value range of z can be adjusted according to the actual situation, and the method is not limited herein.
And obtaining preset comparison parameters based on the small hole imaging and similar triangle principles in the preset geometric processing method.
Then, obtaining a preset proportion parameter according to the pinhole imaging principle and the similar triangle principle in the preset geometric processing method:
h/y1＝z1/f，
h/y2＝z2/f；
determining a second distance parameter and a height parameter according to the preset comparison parameter and the distance difference parameter; and calculating to obtain a horizontal distance parameter from the vehicle to the front target traffic signal lamp and a height parameter of the front target traffic signal lamp at the second moment according to the second distance parameter and the height parameter to obtain an identification result of the traffic signal lamp.
Then, based on the preset proportion parameter, according to the distance and the similar triangle principle, it can be known that:
the distance parameter z2 ═ z × y1/(y1-y2),
the height parameter h ═ z × y1 × y2/(f × y1-y 2));
wherein z, y1, y2 and f are all known quantities, so that the second time t2 is obtained as follows: the horizontal distance parameter z2 from the vehicle to the front target traffic signal lamp is z x Y1/(Y1-Y2) and the height parameter H of the front target traffic signal lamp is Y + z Y1Y 2/(f (Y1-Y2)); the first time t1 and the second time t2 are respectively the distance z1 and z2, and the difference between the distances z; h is the distance from the lower edge of the traffic signal lamp to the horizontal line of the camera on the vehicle; f is the focal length of the camera; y1 is the difference value between the projection of the camera on the vehicle under the traffic light at the time of t1 and the ordinate direction of the reference center point in the camera; z1 is the horizontal distance between the vehicle and the traffic light at time t1, and Y is the camera height.
The embodiment of the present application further provides a traffic light recognition device 200 for automatic driving, and as shown in fig. 2, a schematic structural diagram of the traffic light recognition device for automatic driving in the embodiment of the present application is provided, where the traffic light recognition device 200 for automatic driving at least includes: an obtaining module 210, a detecting module 220, and an identifying module 230, wherein:
in an embodiment of the present application, the obtaining module 210 is specifically configured to: and acquiring image information by using a front camera in the automatic driving vehicle. Namely, the camera is used for shooting the front situation in real time in the running process of the automatic driving vehicle. Real-time processing is required for the image information and relevant recognition results are provided.
In an embodiment of the present application, the detecting module 220 is specifically configured to: usually, an off-line method is adopted to obtain a target detection model through pre-training. The target detection model is obtained by using a plurality of groups of data through machine learning training, and each group of data in the plurality of groups of data comprises: it can be understood that each image data has corresponding label information in its image information.
Preferably, the detection result of the traffic signal lamp in the image information is obtained through a previously trained YoloV5 target detection model.
Specifically, a traffic light detection model is trained by using a YoloV5 model, so that intersection in an image can be detectedA communication signal lamp for outputting the coordinates and size (x) of the center point of the target frame c ，y c ，w 2d ，h 2d ) And the down-edge position of the target frame in the longitudinal direction (fixed in the transverse direction) in the image information can be calculated according to the coordinates and the size of the center point of the output target frame: y is bottom ＝y c +h 2d /2。
In an embodiment of the present application, the identification module 230 is specifically configured to: according to one target frame (usually, only one target frame can be determined when a plurality of target frames exist), such as the largest area of the target frame, in the detection result of the first frame image (arbitrarily selected) in the image information, and according to the target frame (usually, only one target frame can be determined when a plurality of target frames exist, such as the largest area of the target frame) in the detection result of the second frame image in the image information, the geometric relationship between the two target frames obtained from the first frame image and the second frame image can be calculated, and then the identification result of the traffic signal lamp can be obtained.
It should be noted that the two target frames each include an identical target traffic light, that is, both target frames include a unique and identical target traffic light.
Preferably, the recognition result of the traffic light includes the distance between the traffic light and the current vehicle and the height of the traffic light. That is, the relative distance between the traffic signal and the self-vehicle in the recognition result can provide support for making a correct strategy for the speed control of the automatic driving vehicle by means of pure vision and geometric calculation. And the height of the traffic signal lamp in the identification result can keep the automatic driving vehicle at a proper distance from the front vehicle.
It can be understood that the traffic light recognition apparatus for automatic driving described above can implement the steps of the traffic light recognition method for automatic driving provided in the foregoing embodiments, and the related explanations regarding the traffic light recognition method for automatic driving are applicable to the traffic light recognition apparatus for automatic driving, and will not be described herein again.
Fig. 5 is a schematic structural diagram of an electronic device according to an embodiment of the present application. Referring to fig. 5, at a hardware level, the electronic device includes a processor, and optionally further includes an internal bus, a network interface, and a memory. The Memory may include a Memory, such as a Random-Access Memory (RAM), and may further include a non-volatile Memory, such as at least 1 disk Memory. Of course, the electronic device may also include hardware required for other services.
The processor, the network interface, and the memory may be connected to each other via an internal bus, which may be an ISA (Industry Standard Architecture) bus, a PCI (Peripheral Component Interconnect) bus, an EISA (Extended Industry Standard Architecture) bus, or the like. The bus may be divided into an address bus, a data bus, a control bus, etc. For ease of illustration, only one double-headed arrow is shown in FIG. 5, but this does not indicate only one bus or one type of bus.
And the memory is used for storing programs. In particular, the program may include program code comprising computer operating instructions. The memory may include both memory and non-volatile storage and provides instructions and data to the processor.
The processor reads the corresponding computer program from the nonvolatile memory into the memory and then runs the computer program to form the traffic light recognition device for automatic driving on a logic level. The processor is used for executing the program stored in the memory and is specifically used for executing the following operations:
acquiring image information;
obtaining a detection result in the image information through a pre-trained target detection model, wherein the target detection model is obtained by using multiple groups of data through machine learning training, and each group of data in the multiple groups of data comprises: image data and a tag in the image data;
and obtaining the identification result of the traffic signal lamp according to the detection result of the first frame image and the two target frames in the detection result of the second frame image in the image information, wherein the two target frames comprise the same target traffic signal lamp.
The method performed by the traffic signal recognition apparatus for automatic driving according to the embodiment shown in fig. 1 of the present application may be applied to or implemented by a processor. The processor may be an integrated circuit chip having signal processing capabilities. In implementation, the steps of the above method may be performed by integrated logic circuits of hardware in a processor or instructions in the form of software. The Processor may be a general-purpose Processor, including a Central Processing Unit (CPU), a Network Processor (NP), and the like; but also Digital Signal Processors (DSPs), Application Specific Integrated Circuits (ASICs), Field Programmable Gate Arrays (FPGAs) or other Programmable logic devices, discrete Gate or transistor logic devices, discrete hardware components. The various methods, steps, and logic blocks disclosed in the embodiments of the present application may be implemented or performed. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like. The steps of the method disclosed in connection with the embodiments of the present application may be directly implemented by a hardware decoding processor, or implemented by a combination of hardware and software modules in the decoding processor. The software module may be located in ram, flash memory, rom, prom, or eprom, registers, etc. storage media as is well known in the art. The storage medium is located in a memory, and a processor reads information in the memory and completes the steps of the method in combination with hardware of the processor.
The electronic device may further execute the method executed by the traffic light recognition apparatus for automatic driving in fig. 1, and implement the functions of the traffic light recognition apparatus for automatic driving in the embodiment shown in fig. 1, which are not described herein again in this application embodiment.
Embodiments of the present application also provide a computer-readable storage medium storing one or more programs, where the one or more programs include instructions, which when executed by an electronic device including a plurality of application programs, enable the electronic device to perform the method performed by the traffic signal recognition apparatus for automatic driving in the embodiment shown in fig. 1, and specifically to perform:
acquiring image information;
obtaining a detection result in the image information through a pre-trained target detection model, wherein the target detection model is obtained by using multiple groups of data through machine learning training, and each group of data in the multiple groups of data comprises: image data and a tag in the image data;
and obtaining the identification result of the traffic signal lamp according to the detection result of the first frame image and the two target frames in the detection result of the second frame image in the image information, wherein the two target frames comprise the same target traffic signal lamp.
As will be appreciated by one skilled in the art, embodiments of the present invention may be provided as a method, system, or computer program product. Accordingly, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The present invention is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
In a typical configuration, a computing device includes one or more processors (CPUs), input/output interfaces, network interfaces, and memory.
The memory may include forms of volatile memory in a computer readable medium, Random Access Memory (RAM) and/or non-volatile memory, such as Read Only Memory (ROM) or flash memory (flash RAM). Memory is an example of a computer-readable medium.
Computer-readable media, including both non-transitory and non-transitory, removable and non-removable media, may implement information storage by any method or technology. The information may be computer readable instructions, data structures, modules of a program, or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), Static Random Access Memory (SRAM), Dynamic Random Access Memory (DRAM), other types of Random Access Memory (RAM), Read Only Memory (ROM), Electrically Erasable Programmable Read Only Memory (EEPROM), flash memory or other memory technology, compact disc read only memory (CD-ROM), Digital Versatile Discs (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices, or any other non-transmission medium that can be used to store information that can be accessed by a computing device. As defined herein, a computer readable medium does not include a transitory computer readable medium such as a modulated data signal and a carrier wave.
It should also be noted that the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other like elements in a process, method, article, or apparatus that comprises the element.
As will be appreciated by one skilled in the art, embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The above description is only an example of the present application and is not intended to limit the present application. Various modifications and changes may occur to those skilled in the art. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included in the scope of the claims of the present application.
Claims (10)
1. A traffic light identification method for autonomous driving, wherein for an autonomous driving vehicle, the method comprises:
acquiring image information;
obtaining a detection result in the image information through a pre-trained target detection model, wherein the target detection model is obtained by using multiple groups of data through machine learning training, and each group of data in the multiple groups of data comprises: image data and a label in the image data;
and obtaining the identification result of the traffic signal lamp according to the detection result of the first frame image and the two target frames in the detection result of the second frame image in the image information, wherein the two target frames comprise the same target traffic signal lamp.
2. The method of claim 1, wherein the recognition result of the traffic light includes a distance of the traffic light from the current vehicle itself and a height of the traffic light.
3. The method of claim 2, further comprising:
under the condition that the pre-loaded high-precision map data is invalid, obtaining the distance between the traffic signal lamp and the current vehicle and the height of the traffic signal lamp in the identification result of the traffic signal lamp; and
and/or under the condition that the size of the traffic signal lamp is unknown, obtaining the distance between the traffic signal lamp in the identification result of the traffic signal lamp and the current vehicle and the height of the traffic signal lamp.
4. The method of claim 1, wherein the detection result in the image information is obtained by a pre-trained object detection model, wherein the object detection model is obtained by machine learning training using a plurality of sets of data, and each set of data in the plurality of sets of data comprises: a sample image and the sample image label comprising:
obtaining the position coordinates of a target frame of a traffic signal lamp in the image information and the size of the target frame through a pre-trained target detection model;
and obtaining longitudinal and lower edge position information of the target frame in the image information according to the position coordinates of the target frame of the traffic signal lamp and the size of the target frame.
5. The method of claim 1, wherein the obtaining of the traffic signal recognition result according to two target frames in the detection results of the first frame image and the second frame image in the image information, wherein the two target frames include a same target traffic signal, comprises:
determining a first frame image corresponding to the first moment and a second frame image corresponding to a second moment, wherein the second moment is greater than the first moment and meets the requirement of the distance between the corresponding moment and the vehicle, and the first moment is selected arbitrarily;
and obtaining the identification result of the traffic signal lamp according to the target frame in the detection result of the first frame image and the target frame in the detection result of the second frame image in the image information and a preset geometric processing method.
6. The method as claimed in claim 5, wherein the obtaining of the recognition result of the traffic signal lamp according to the target frame in the detection result of the first frame image and the target frame in the detection result of the second frame image in the image information and the preset geometric processing method comprises:
determining a distance difference parameter according to the self-advancing distance corresponding to the first moment and the self-advancing distance corresponding to the second moment;
obtaining preset comparison parameters based on small hole imaging and a similar triangle principle in a preset geometric processing method;
determining a second distance parameter and a height parameter according to the preset comparison parameter and the distance difference parameter;
and calculating to obtain a horizontal distance parameter from the vehicle to the front target traffic signal lamp and a height parameter of the front target traffic signal lamp at the second moment according to the second distance parameter and the height parameter to obtain an identification result of the traffic signal lamp.
7. The method of claim 1, wherein obtaining the detection result in the image information through a pre-trained object detection model comprises:
and obtaining a detection result of the traffic signal lamp in the image information through a pre-trained YoloV5 target detection model.
8. A traffic signal light recognition apparatus for automatic driving, wherein the apparatus comprises:
the acquisition module is used for acquiring image information;
the detection module is used for obtaining a detection result in the image information through a pre-trained target detection model, wherein the target detection model is obtained by using multiple groups of data through machine learning training, and each group of data in the multiple groups of data comprises: image data and a tag in the image data;
and the identification module is used for obtaining the identification result of the traffic signal lamp according to the detection result of the first frame image and the two target frames in the detection result of the second frame image in the image information, wherein the two target frames comprise the same target traffic signal lamp.
9. An electronic device, comprising:
a processor; and
a memory arranged to store computer executable instructions which, when executed, cause the processor to perform the method of any of claims 1 to 7.
10. A computer readable storage medium storing one or more programs which, when executed by an electronic device comprising a plurality of application programs, cause the electronic device to perform the method of any of claims 1-7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210629737.4A CN114842452A (en) | 2022-06-02 | 2022-06-02 | Traffic signal lamp identification method, device and equipment for automatic driving |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210629737.4A CN114842452A (en) | 2022-06-02 | 2022-06-02 | Traffic signal lamp identification method, device and equipment for automatic driving |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114842452A true CN114842452A (en) | 2022-08-02 |
Family
ID=82574433
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210629737.4A Pending CN114842452A (en) | 2022-06-02 | 2022-06-02 | Traffic signal lamp identification method, device and equipment for automatic driving |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114842452A (en) |
-
2022
- 2022-06-02 CN CN202210629737.4A patent/CN114842452A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN115143952A (en) | Automatic driving vehicle positioning method and device based on visual assistance | |
| CN115507862A (en) | Lane line positioning method and device, electronic device and storage medium | |
| CN114973198A (en) | Course angle prediction method and device of target vehicle, electronic equipment and storage medium | |
| CN114547222A (en) | Semantic map construction method and device and electronic equipment | |
| CN115546315A (en) | Sensor on-line calibration method and device for automatic driving vehicle and storage medium | |
| CN114966632A (en) | Laser radar calibration method and device, electronic equipment and storage medium | |
| CN111191482B (en) | Brake lamp identification method and device and electronic equipment | |
| CN115950441B (en) | Fusion positioning method and device for automatic driving vehicle and electronic equipment | |
| CN116990776A (en) | Laser radar point cloud compensation method and device, electronic equipment and storage medium | |
| CN113804214B (en) | Vehicle positioning method and device, electronic equipment and computer readable storage medium | |
| CN114842452A (en) | Traffic signal lamp identification method, device and equipment for automatic driving | |
| CN113903014B (en) | Lane line prediction method and device, electronic device and computer-readable storage medium | |
| CN115620277A (en) | Monocular 3D environment sensing method and device, electronic equipment and storage medium | |
| CN115112125A (en) | Positioning method and device for automatic driving vehicle, electronic equipment and storage medium | |
| CN114739416A (en) | Automatic driving vehicle positioning method and device, electronic equipment and storage medium | |
| CN114066958A (en) | Method and device for predicting depth information of target, electronic device and storage medium | |
| CN114677458A (en) | Road mark generation method and device for high-precision map, electronic equipment and storage medium | |
| CN114705121B (en) | Vehicle pose measurement method and device, electronic equipment and storage medium | |
| CN116994179A (en) | Target tracking method and device and electronic equipment | |
| CN113538546B (en) | Target detection method, device and equipment for automatic driving | |
| CN113822261A (en) | Traffic signal lamp detection method and device, electronic equipment and storage medium | |
| CN114705121A (en) | Vehicle pose measuring method and device, electronic equipment and storage medium | |
| CN115546752A (en) | Lane line marking method and device for high-precision map, electronic equipment and storage medium | |
| CN114723947A (en) | Method and device for dividing road surface full-element image, electronic device and storage medium | |
| CN114723819A (en) | Calibration method and device for automatic driving vehicle, electronic 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 |