CN112906471A - Traffic signal lamp identification method and device - Google Patents
Traffic signal lamp identification method and device Download PDFInfo
- Publication number
- CN112906471A CN112906471A CN202110065037.2A CN202110065037A CN112906471A CN 112906471 A CN112906471 A CN 112906471A CN 202110065037 A CN202110065037 A CN 202110065037A CN 112906471 A CN112906471 A CN 112906471A
- Authority
- CN
- China
- Prior art keywords
- signal lamp
- state
- identified
- traffic signal
- traffic
- 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
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/70—Determining position or orientation of objects or cameras
- G06T7/73—Determining position or orientation of objects or cameras using feature-based methods
- G06T7/74—Determining position or orientation of objects or cameras using feature-based methods involving reference images or patches
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/80—Analysis of captured images to determine intrinsic or extrinsic camera parameters, i.e. camera calibration
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/09—Arrangements for giving variable traffic instructions
- G08G1/0962—Arrangements for giving variable traffic instructions having an indicator mounted inside the vehicle, e.g. giving voice messages
- G08G1/0967—Systems involving transmission of highway information, e.g. weather, speed limits
- G08G1/096708—Systems involving transmission of highway information, e.g. weather, speed limits where the received information might be used to generate an automatic action on the vehicle control
- G08G1/096725—Systems involving transmission of highway information, e.g. weather, speed limits where the received information might be used to generate an automatic action on the vehicle control where the received information generates an automatic action on the vehicle control
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20081—Training; Learning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20092—Interactive image processing based on input by user
- G06T2207/20104—Interactive definition of region of interest [ROI]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30248—Vehicle exterior or interior
- G06T2207/30252—Vehicle exterior; Vicinity of vehicle
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Data Mining & Analysis (AREA)
- Life Sciences & Earth Sciences (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Evolutionary Computation (AREA)
- Evolutionary Biology (AREA)
- General Engineering & Computer Science (AREA)
- Bioinformatics & Computational Biology (AREA)
- Artificial Intelligence (AREA)
- Multimedia (AREA)
- Atmospheric Sciences (AREA)
- Traffic Control Systems (AREA)
Abstract
The invention provides a traffic signal lamp identification method and a traffic signal lamp identification device, wherein the method comprises the following steps: acquiring signal lamp data of a traffic signal lamp to be identified; identifying a first signal lamp state of a traffic signal lamp to be identified at the current moment according to the signal lamp data; updating the counting value according to the state of the first signal lamp and the state of the second signal lamp at the previous moment; and determining the state of the first signal lamp corresponding to the updated counting value reaching the preset threshold value as the signal lamp state of the signal lamp to be identified. The first signal lamp state at the current moment is output after the counting value is accumulated to the preset threshold value, the probability of error in signal lamp state identification caused by jumping of the traffic signal lamp to be identified in the process of analyzing the traffic signal lamp to be identified is greatly reduced, the signal lamp data of a plurality of traffic signal lamps to be identified are obtained, the signal lamp state obtained by combining the signal lamp data of the traffic signal lamps to be identified is combined, and the influence of a complex scene on the identification result can be reduced.
Description
Technical Field
The invention relates to the technical field of self-driving, in particular to a traffic signal lamp identification method and device.
Background
In the field of automated driving, the identification of traffic lights is an important module in automated driving, marking automated driving in open road scenes, such as closed roads, such as highways, going to urban roads. The traditional method for identifying the traffic signal lamp according to the color features based on color gamut conversion is poor in robustness, a large amount of false detections can be generated in the face of complex scenes, particularly, the tail lamp of an automobile can generate serious interference on detection results at night, and the traffic signal lamp is changed when the traffic signal lamp is identified due to the fact that the traffic signal lamp is a dynamic traffic signal.
Disclosure of Invention
Therefore, the technical problem to be solved by the present invention is to overcome the defect in the prior art that it is difficult to accurately identify a traffic signal, and to provide a method and an apparatus for identifying a traffic signal.
The invention provides a traffic signal lamp identification method in a first aspect, which comprises the following steps: acquiring signal lamp data of a traffic signal lamp to be identified; identifying a first signal lamp state of a traffic signal lamp to be identified at the current moment according to the signal lamp data; updating the counting value according to the state of the first signal lamp and the state of a second signal lamp at a moment on the traffic signal lamp to be identified; and determining the state of the first signal lamp corresponding to the updated counting value reaching the preset threshold value as the signal lamp state of the signal lamp to be identified.
Optionally, in the traffic signal light recognition method provided by the present invention, the step of recognizing the first signal light state of the traffic signal light to be recognized according to the signal light data, where the signal light data is image data including the traffic signal light to be recognized, includes: determining position information and calibration parameters of equipment for acquiring image information of the traffic signal lamp to be identified; extracting an interested area from the image data according to preset map data, image data, position information and calibration parameters which contain the traffic signal lamp to be identified, wherein the interested area contains the traffic signal lamp to be identified; and inputting the region of interest into a preset signal lamp identification model to obtain a first signal lamp state.
Optionally, in the traffic signal light recognition method provided by the present invention, the step of updating the count value according to the first signal light state and the second signal light state at a time on the traffic signal light to be recognized includes: if the first signal lamp state is the same as the second signal lamp state, adding one to the counting value; if the first signal lamp state is different from the second signal lamp state, the counting value is decreased by one.
Optionally, in the traffic signal light recognition method provided by the present invention, the method further includes: if the counting value is smaller than the preset threshold value, the step of obtaining the signal lamp data of the traffic signal lamp to be identified is repeatedly executed, the step of updating the counting value according to the first signal lamp state and the second signal lamp state at the last moment of the traffic signal lamp to be identified is repeated until the updated counting value reaches the preset threshold value, and the corresponding first signal lamp state is determined as the signal lamp state of the traffic signal lamp to be identified when the updated counting value reaches the preset threshold value.
Optionally, in the traffic signal light recognition method provided by the present invention, the method further includes: acquiring position information of a target vehicle; determining the distance between the target vehicle and the traffic signal lamp to be identified according to the position information of the target vehicle and the map data; and if the distance between the target vehicle and the traffic signal lamp is smaller than a preset threshold value, determining the first signal lamp state of the to-be-identified signal lamp at the current moment as the signal lamp state of the to-be-identified signal lamp.
Optionally, in the traffic signal lamp identification method provided by the present invention, the preset signal lamp identification model includes a signal lamp color identification submodule and a signal lamp shape identification submodule, and the first signal lamp state is obtained by inputting the region of interest into the preset signal lamp identification model, including: inputting the region of interest into a preset signal lamp identification model, and obtaining a signal lamp color state according to a signal lamp color identification submodule; inputting the region of interest into a preset signal lamp identification model, and identifying a submodule according to the shape of a signal lamp to obtain the shape state of the signal lamp; and obtaining a first signal lamp state according to the signal lamp color state and the signal lamp shape state.
Optionally, in the traffic signal light recognition method provided by the present invention, after the step of determining the first signal light state as the signal light state of the signal light to be recognized, the method further includes: the count value is reset.
A second aspect of the present invention provides a traffic signal light recognition apparatus, including: the signal lamp data acquisition module is used for acquiring signal lamp data of the traffic signal lamp to be identified; the first signal lamp state identification module is used for identifying the state of a first signal lamp of the traffic signal lamp to be identified at the current moment according to the signal lamp data; the counting value updating module is used for updating the counting value according to the state of the first signal lamp and the state of a second signal lamp at a moment on the traffic signal lamp to be identified; and the signal lamp state determining module is used for determining the corresponding first signal lamp state as the signal lamp state of the signal lamp to be identified when the updated counting value reaches the preset threshold value.
A third aspect of the present invention provides a computer apparatus comprising: at least one processor; and a memory communicatively coupled to the at least one processor; wherein the memory stores instructions executable by the at least one processor, the instructions being executable by the at least one processor to perform the traffic signal identification method as provided by the first aspect of the invention.
A fourth aspect of the present invention provides a computer-readable storage medium storing computer instructions for causing a computer to execute the traffic signal identification method according to the first aspect of the present invention.
The technical scheme of the invention has the following advantages:
the method and the device for identifying the traffic signal lamp identify the states of the traffic signal lamp to be identified at a plurality of continuous moments, determine the state of the first signal lamp at the current moment as the state of the traffic signal lamp to be identified only after the accumulated counting value reaches the preset threshold value, and continuously keep one state for a period of time although the state of the traffic signal lamp to be identified is dynamic, so that the state of the first signal lamp at the current moment is compared with the state of the signal lamp at the previous moment when the first signal lamp at the current moment is obtained by identification, the counting value is updated according to the comparison result, the state of the first signal lamp at the current moment is output after the counting value is accumulated to the preset threshold value, and the probability of error of signal lamp state identification caused by jumping of the traffic signal lamp to be identified in the process of analyzing the traffic signal lamp to be identified is greatly reduced, moreover, the signal lamp data of a plurality of traffic signal lamps to be identified are acquired, and the signal lamp states obtained by combining the signal lamp data of the plurality of traffic signal lamps to be identified can also reduce the influence of a complex scene on the identification result, so that the signal lamp states of the traffic signal lamps to be identified can be more accurately determined by implementing the method and the device.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, and it is obvious that the drawings in the following description are some embodiments of the present invention, and other drawings can be obtained by those skilled in the art without creative efforts.
FIG. 1 is a flow chart of a specific example of a traffic signal light identification method in an embodiment of the present invention;
FIG. 2 is a flow chart of another specific example of a traffic signal light identification method in an embodiment of the present invention;
FIG. 3 is a flowchart of yet another specific example of a traffic signal light identification method in an embodiment of the present invention;
FIG. 4 is a schematic block diagram of a specific example of a traffic signal light identification device in an embodiment of the present invention;
fig. 5 is a schematic block diagram of a specific example of a computer device in the embodiment of the present invention.
Detailed Description
The technical solutions of the present invention will be described clearly and completely with reference to the accompanying drawings, and it should be understood that the described embodiments are some, but not all embodiments of the present invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
In the description of the present invention, it should be noted that the terms "first", "second", and "third" are used for descriptive purposes only and are not to be construed as indicating or implying relative importance.
In addition, the technical features involved in the different embodiments of the present invention described below may be combined with each other as long as they do not conflict with each other.
The embodiment of the invention provides a traffic signal lamp identification method, as shown in fig. 1, comprising the following steps:
step S10: and acquiring signal lamp data of the traffic signal lamp to be identified.
In an alternative embodiment, the signal light data of the traffic signal to be identified may be image data of the traffic signal to be identified acquired by an image acquiring device mounted on the target vehicle.
Step S20: and identifying the state of a first signal lamp of the traffic signal lamp to be identified at the current moment according to the signal lamp data.
In an optional embodiment, the signal lamp data acquired at the current time may be input into a preset signal lamp identification model, so as to obtain a first signal lamp state, where the first signal lamp state may include the color and shape of the signal lamp to be identified, the color of the signal lamp to be identified includes red, yellow, green, and black, and the shape of the signal lamp to be identified includes a left arrow, an up arrow, a right arrow, and the like.
Step S30: and updating the counting value according to the state of the first signal lamp and the state of a second signal lamp at the last moment of the traffic signal lamp to be identified.
In an optional embodiment, the first signal lamp state is compared with the second signal lamp state at the previous moment, and if the first signal lamp state is the same as the second signal lamp state, one is added on the basis of the current counting value; if the status of one signal lamp is different from the status of the second signal lamp, then one is subtracted from the current count value.
Step S40: and determining the state of the first signal lamp corresponding to the updated counting value reaching the preset threshold value as the signal lamp state of the signal lamp to be identified. In a specific embodiment, the preset threshold may be set to 15, that is, when the updated count value is 15, the current first signal lamp state is determined as the signal lamp state of the signal lamp to be identified.
In an alternative embodiment, if the count value is smaller than the predetermined threshold, the process returns to step S10.
The traffic signal lamp identification method provided by the embodiment of the invention identifies the states of the traffic signal lamps to be identified at a plurality of continuous moments, only when the accumulated counting value reaches the preset threshold value, the first signal lamp state at the current moment is determined as the state of the traffic signal lamp to be identified, although the signal lamp state of the traffic signal lamp to be identified is dynamic, the first signal lamp state at the current moment can be continuously maintained for a period of time, therefore, when the first signal lamp state at the current moment is obtained by identification, the first signal lamp state at the current moment is compared with the signal lamp state at the previous moment, the counting value is updated according to the comparison result, the first signal lamp state at the current moment is output after the counting value is accumulated to the preset threshold value, and the probability of error of signal lamp state identification caused by jumping of the traffic signal lamp to be identified in the process of analyzing the traffic signal lamps to be identified is greatly reduced, moreover, the signal lamp data of the traffic signal lamps to be identified are acquired, and the signal lamp states obtained by combining the signal lamp data of the traffic signal lamps to be identified can reduce the influence of a complex scene on the identification result, so that the signal lamp states of the traffic signal lamps to be identified can be more accurately determined by implementing the embodiment of the invention.
In an optional embodiment, in the traffic signal light identification method provided in the embodiment of the present invention, the signal light data is image data including a traffic signal light to be identified, as shown in fig. 2, the step S20 specifically includes:
step S21: and determining the position information and the calibration parameters of the equipment for acquiring the image information of the traffic signal lamp to be identified.
In an alternative embodiment, if the image information of the traffic signal to be identified is acquired by an image capturing device installed on the target vehicle, and the above-mentioned steps S10-S40 are executed by a data processing apparatus installed on the target vehicle, the position information of the device that captures the image information of the traffic signal to be identified may be determined according to the position information of the target vehicle; if the image information of the traffic signal lamp to be recognized is acquired through the image acquisition device installed at a fixed position near the traffic signal lamp to be recognized, the above steps S10-S40 are executed by the cloud platform connected to the image acquisition device, and the target vehicle acquires the signal lamp state of the traffic signal lamp to be recognized according to the cloud platform, the position information of the device acquiring the image information of the traffic signal lamp to be recognized may be preset. In the embodiment of the invention, the equipment for acquiring the image information of the traffic signal lamp to be identified is taken as the image acquisition equipment installed on the target vehicle.
The calibration parameters of the device for acquiring the image information of the traffic signal lamp to be identified comprise internal parameters and external parameters of the image acquisition device, wherein the internal parameters are parameters related to the characteristics of the image acquisition device, such as the focal length, the pixel size and the like of the image acquisition device, and the external parameters comprise the position, the rotation direction and the like of the image acquisition device relative to the traffic signal lamp to be identified.
Step S22: and extracting an interested area from the image data according to preset map data, image data, position information and calibration parameters which contain the traffic signal lamp to be identified, wherein the interested area contains the traffic signal lamp to be identified. The purpose of extracting the region of interest (ROI) is to filter out most irrelevant backgrounds, such as a ground region and a sky region, and screen out an approximate region including a traffic signal lamp, so as to improve the calculation speed of detecting the traffic signal lamp to be identified.
In an alternative implementation, when extracting the region of interest, the positions of the traffic signal lamp to be identified and the image acquisition device in the map data may be determined first, and determining the relative positions of the traffic signal lamp to be identified and the image acquisition equipment, thereby converting the traffic signal lamp to be identified into a coordinate system constructed by the image acquisition equipment, then converting the traffic signal lamp to be identified into an image coordinate system of image data based on the position of the traffic signal lamp to be identified in the coordinate system constructed by the image acquisition equipment, the calibration parameter of the image acquisition equipment and the imaging model, thereby extracting a region of interest ROI (x, y, w, h) according to the position of the traffic signal lamp to be identified in the image coordinate system, wherein (x, y) is the coordinates of the top left vertex of the ROI area in the original image, and (w, h) is the width and height of the ROI area, and the ROI area is used as the input of traffic light detection. In one embodiment, if the image information of the traffic signal to be identified is acquired by an image capturing device installed on the target vehicle, the coordinate system constructed by the image capturing device may be a vehicle body coordinate system.
Step S23: and inputting the region of interest into a preset signal lamp identification model to obtain a first signal lamp state.
In an alternative embodiment, since most of the environment information in the region of interest obtained in step S22 is only cropped, but the environment information still exists in the region of interest, before the region of interest is input into the preset signal lamp positioning model, the region of interest should also be input into the preset signal lamp positioning model, and the position of the signal lamp in the region of interest is determined by the preset signal lamp positioning model, the input of the preset signal lamp positioning model is the minimum bounding rectangle (x1, y1, w1, h1) of the signal lamp in the region of interest and the confidence coefficient according to the region of interest, where (x1, y1) is the coordinates of the top left vertex of the signal lamp in the image after cropping, (w1, h1) is the width and height of the signal lamp in the image, and the confidence coefficient can be used to describe the probability that the detection box contains the traffic signal lamp to be identified, some redundant detection frames are filtered out through confidence, for example, when the confidence in a certain detection frame is less than a certain value, the detection frame is judged not to contain the traffic signal to be identified, and the detection frame can be considered to be invalid.
After the signal lamp is positioned, the positioned interesting area is input into a preset signal lamp identification model, and a first signal lamp state is obtained.
In an optional embodiment, the preset signal lamp identification model is a single-input dual-output network structure, and includes a signal lamp color identification submodule and a signal lamp shape identification submodule, and the step of obtaining the first signal lamp state according to the region of interest by the preset signal lamp identification model specifically includes: identifying the submodule according to the color of the signal lamp to obtain the color state of the signal lamp; identifying the submodule according to the shape of the signal lamp to obtain the shape state of the signal lamp; and obtaining a first signal lamp state according to the signal lamp color state and the signal lamp shape state.
According to the embodiment of the invention, the task of identifying the color state of the signal lamp and the task of identifying the shape of the signal lamp are separated and decoupled, so that the conflict among different tasks is reduced.
In an optional embodiment, when the preset signal lamp identification model and the preset signal lamp identification model are trained, the principle of gradient descent is adopted, when the loss functions of the preset signal lamp identification model and the preset signal lamp identification model converge to respective threshold value ranges, the training is stopped, and the model obtained by current training is used for positioning and identifying the traffic signal lamp to be identified.
In an optional embodiment, in the traffic signal light identification method provided in the embodiment of the present invention, as shown in fig. 3, the method further includes:
step S50: position information of a target vehicle is acquired.
Step S60: and determining the distance between the target vehicle and the traffic signal lamp to be identified according to the position information of the target vehicle and the map data.
Step S70: and judging whether the distance between the target vehicle and the traffic signal lamp is smaller than a preset threshold value, if so, determining the first signal lamp state of the to-be-identified signal lamp at the current moment as the signal lamp state of the to-be-identified signal lamp, and if not, returning to the step S10.
By the embodiment of the invention, the problem that the target vehicle cannot be controlled in time because the signal lamp state of the traffic signal lamp to be identified still cannot be determined when the target vehicle is adjacent to the traffic signal lamp to be identified can be solved.
In an alternative embodiment, after the signal status of the signal to be identified is obtained in the above step S40, the counting value should be reset so as to execute the next traffic signal identification.
An embodiment of the present invention further provides a traffic signal light recognition apparatus, as shown in fig. 4, including:
the signal light data acquiring module 10 is configured to acquire signal light data of a traffic signal to be identified, for details, refer to the description of step S10 in the foregoing embodiment.
The first signal lamp state identification module 20 is configured to identify the first signal lamp state of the traffic signal lamp to be identified at the current time according to the signal lamp data, and the details refer to the description of step S20 in the foregoing embodiment.
The count value updating module 30 is configured to update the count value according to the first signal light state and the second signal light state at a time on the traffic signal to be identified, for details, refer to the description of step S30 in the foregoing embodiment.
The signal lamp state determining module 40 is configured to determine, as the signal lamp state of the signal lamp to be identified, the first signal lamp state corresponding to the updated count value reaching the preset threshold, for details, refer to the description of step S40 in the foregoing embodiment.
The traffic signal lamp recognition device provided by the invention recognizes the states of the traffic signal lamps to be recognized at a plurality of continuous moments, determines the state of the first signal lamp at the current moment as the state of the traffic signal lamp to be recognized only after the accumulated counting value reaches the preset threshold value, and continuously maintains one state for a period of time although the state of the traffic signal lamp to be recognized is dynamic, so that the state of the first signal lamp at the current moment is compared with the state of the signal lamp at the previous moment when the state of the first signal lamp at the current moment is obtained by recognition, the counting value is updated according to the comparison result, the state of the first signal lamp at the current moment is output after the counting value is accumulated to the preset threshold value, and the probability of error of signal lamp state recognition caused by the jump of the traffic signal lamp to be recognized in the process of analyzing the traffic signal lamps to be recognized is greatly reduced, moreover, the signal lamp data of a plurality of traffic signal lamps to be identified are acquired, and the signal lamp states obtained by combining the signal lamp data of the plurality of traffic signal lamps to be identified can also reduce the influence of a complex scene on the identification result, so that the signal lamp states of the traffic signal lamps to be identified can be more accurately determined by implementing the method and the device.
An embodiment of the present invention provides a computer device, as shown in fig. 5, the computer device mainly includes one or more processors 51 and a memory 52, and one processor 51 is taken as an example in fig. 5.
The computer device may further include: an input device 53 and an output device 54.
The processor 51, the memory 52, the input device 53 and the output device 54 may be connected by a bus or other means, and fig. 5 illustrates the connection by a bus as an example.
The processor 51 may be a Central Processing Unit (CPU). The Processor 51 may also be other general purpose processors, 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, or combinations thereof. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like. The memory 52 may include a storage program area and a storage data area, wherein the storage program area may store an operating system, an application program required for at least one function; the storage data area may store data created from use of the traffic signal light recognition device, and the like. Further, the memory 52 may include high speed random access memory, and may also include non-transitory memory, such as at least one magnetic disk storage device, flash memory device, or other non-transitory solid state storage device. In some embodiments, the memory 52 optionally includes memory located remotely from the processor 51, and these remote memories may be connected to the traffic light identification device via a network. The input device 53 may receive a calculation request (or other numeric or character information) input by a user and generate a key signal input associated with a traffic signal recognition device. The output device 54 may include a display device such as a display screen for outputting the calculation result.
Embodiments of the present invention provide a computer-readable storage medium, where the computer-readable storage medium stores computer instructions, and the computer-readable storage medium stores computer-executable instructions, where the computer-executable instructions may execute the traffic signal light identification method in any of the above method embodiments. The storage medium may be a magnetic Disk, an optical Disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a Flash Memory (Flash Memory), a Hard Disk (Hard Disk Drive, abbreviated as HDD) or a Solid State Drive (SSD), etc.; the storage medium may also comprise a combination of memories of the kind described above.
It should be understood that the above examples are only for clarity of illustration and are not intended to limit the embodiments. Other variations and modifications will be apparent to persons skilled in the art in light of the above description. And are neither required nor exhaustive of all embodiments. And obvious variations or modifications therefrom are within the scope of the invention.
Claims (10)
1. A traffic signal lamp identification method is characterized by comprising the following steps:
acquiring signal lamp data of a traffic signal lamp to be identified;
identifying a first signal lamp state of the traffic signal lamp to be identified at the current moment according to the signal lamp data;
updating a counting numerical value according to the state of the first signal lamp and the state of a second signal lamp at a moment on the traffic signal lamp to be identified;
and determining the state of the first signal lamp corresponding to the updated counting value reaching a preset threshold value as the signal lamp state of the signal lamp to be identified.
2. The traffic signal light identification method according to claim 1, wherein the signal light data is image data containing a traffic signal to be identified,
the step of identifying a first signal lamp state of the traffic signal lamp to be identified according to the signal lamp data comprises the following steps:
determining position information and calibration parameters of equipment for acquiring the image information of the traffic signal lamp to be identified;
extracting an interested area from the image data according to preset map data containing the traffic signal lamp to be identified, the image data, the position information and the calibration parameters, wherein the interested area contains the traffic signal lamp to be identified;
and inputting the region of interest into a preset signal lamp identification model to obtain the state of the first signal lamp.
3. The traffic signal light identification method of claim 1, wherein the step of updating the count value based on the first signal light state and a second signal light state at a time on the traffic signal to be identified comprises:
if the first signal lamp state is the same as the second signal lamp state, adding one to the counting number;
and if the first signal lamp state is different from the second signal lamp state, the counting value is reduced by one.
4. The traffic signal light identification method according to any one of claims 1-3, further comprising:
if the counting value is smaller than the preset threshold value, the step of obtaining signal lamp data of the traffic signal lamp to be identified is repeatedly executed, the step of updating the counting value according to the first signal lamp state and a second signal lamp state at the moment on the traffic signal lamp to be identified is repeated until the updated counting value reaches the preset threshold value, and the first signal lamp state corresponding to the updated counting value reaching the preset threshold value is determined as the signal lamp state of the traffic signal lamp to be identified.
5. The traffic signal light identification method according to claim 2, further comprising:
acquiring position information of a target vehicle;
determining the distance between the target vehicle and the traffic signal lamp to be identified according to the position information of the target vehicle and the map data;
and if the distance between the target vehicle and the traffic signal lamp is smaller than a preset threshold value, determining the first signal lamp state of the signal lamp to be identified at the current moment as the signal lamp state of the signal lamp to be identified.
6. The traffic signal light identification method according to claim 2, wherein the preset signal light identification model includes a signal light color identification submodule and a signal light shape identification submodule,
inputting the region of interest into a preset signal lamp identification model to obtain the first signal lamp state, wherein the method comprises the following steps:
inputting the region of interest into a preset signal lamp identification model, and obtaining a signal lamp color state according to the signal lamp color identification submodule;
inputting the region of interest into a preset signal lamp identification model, and obtaining a signal lamp shape state according to the signal lamp shape identification submodule;
and obtaining the first signal lamp state according to the signal lamp color state and the signal lamp shape state.
7. The traffic signal light identification method according to claim 1, further comprising, after the step of determining the first signal light state as the signal light state of the signal light to be identified:
resetting the count value.
8. A traffic signal light identification device, comprising:
the signal lamp data acquisition module is used for acquiring signal lamp data of the traffic signal lamp to be identified;
the first signal lamp state identification module is used for identifying the first signal lamp state of the traffic signal lamp to be identified at the current moment according to the signal lamp data;
the counting value updating module is used for updating the counting value according to the state of the first signal lamp and the state of a second signal lamp at a moment on the traffic signal lamp to be identified;
and the signal lamp state determining module is used for determining the first signal lamp state corresponding to the updated counting value reaching a preset threshold as the signal lamp state of the signal lamp to be identified.
9. A computer device, comprising:
at least one processor; and a memory communicatively coupled to the at least one processor; wherein the memory stores instructions executable by the at least one processor to perform the traffic signal identification method of any of claims 1-7.
10. A computer-readable storage medium storing computer instructions for causing a computer to perform the traffic signal identification method according to any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110065037.2A CN112906471A (en) | 2021-01-18 | 2021-01-18 | Traffic signal lamp identification method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110065037.2A CN112906471A (en) | 2021-01-18 | 2021-01-18 | Traffic signal lamp identification method and device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112906471A true CN112906471A (en) | 2021-06-04 |
Family
ID=76115932
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110065037.2A Pending CN112906471A (en) | 2021-01-18 | 2021-01-18 | Traffic signal lamp identification method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112906471A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113450588A (en) * | 2021-06-28 | 2021-09-28 | 通视(天津)信息技术有限公司 | Method and device for processing information during traffic signal lamp and electronic equipment |
| CN114613171A (en) * | 2022-01-21 | 2022-06-10 | 北京佰才邦技术股份有限公司 | Signal lamp state information determination method, electronic device and storage medium |
| CN114662735A (en) * | 2022-02-14 | 2022-06-24 | 北京佰才邦技术股份有限公司 | Traffic signal lamp law prediction method, system and storage medium |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103177256A (en) * | 2013-04-02 | 2013-06-26 | 上海理工大学 | Method for identifying display state of traffic signal lamp |
| CN105832501A (en) * | 2016-03-23 | 2016-08-10 | 京东方科技集团股份有限公司 | Blind person navigation method and blind person navigation equipment |
| CN109215364A (en) * | 2018-11-19 | 2019-01-15 | 长沙智能驾驶研究院有限公司 | Traffic signals recognition methods, system, equipment and storage medium |
| CN109598244A (en) * | 2018-12-07 | 2019-04-09 | 吉林大学 | A kind of traffic lights identifying system and its recognition methods |
-
2021
- 2021-01-18 CN CN202110065037.2A patent/CN112906471A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103177256A (en) * | 2013-04-02 | 2013-06-26 | 上海理工大学 | Method for identifying display state of traffic signal lamp |
| CN105832501A (en) * | 2016-03-23 | 2016-08-10 | 京东方科技集团股份有限公司 | Blind person navigation method and blind person navigation equipment |
| CN109215364A (en) * | 2018-11-19 | 2019-01-15 | 长沙智能驾驶研究院有限公司 | Traffic signals recognition methods, system, equipment and storage medium |
| CN109598244A (en) * | 2018-12-07 | 2019-04-09 | 吉林大学 | A kind of traffic lights identifying system and its recognition methods |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113450588A (en) * | 2021-06-28 | 2021-09-28 | 通视(天津)信息技术有限公司 | Method and device for processing information during traffic signal lamp and electronic equipment |
| CN113450588B (en) * | 2021-06-28 | 2023-04-07 | 通视(天津)信息技术有限公司 | Method and device for processing information during traffic signal lamp and electronic equipment |
| CN114613171A (en) * | 2022-01-21 | 2022-06-10 | 北京佰才邦技术股份有限公司 | Signal lamp state information determination method, electronic device and storage medium |
| CN114613171B (en) * | 2022-01-21 | 2023-08-18 | 北京佰才邦技术股份有限公司 | Signal lamp state information determining method, electronic device and storage medium |
| CN114662735A (en) * | 2022-02-14 | 2022-06-24 | 北京佰才邦技术股份有限公司 | Traffic signal lamp law prediction method, system and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| EP3806064B1 (en) | Method and apparatus for detecting parking space usage condition, electronic device, and storage medium | |
| CN112906471A (en) | Traffic signal lamp identification method and device | |
| CN108550258B (en) | Vehicle queuing length detection method and device, storage medium and electronic equipment | |
| CN112163543A (en) | Method and system for detecting illegal lane occupation of vehicle | |
| CN112329881B (en) | License plate recognition model training method, license plate recognition method and device | |
| CN112052815B (en) | Behavior detection method and device and electronic equipment | |
| CN109726678B (en) | License plate recognition method and related device | |
| CN112949578B (en) | Vehicle lamp state identification method, device, equipment and storage medium | |
| CN111435446A (en) | License plate identification method and device based on L eNet | |
| CN111967396A (en) | Processing method, device and equipment for obstacle detection and storage medium | |
| CN115761668A (en) | Camera stain recognition method and device, vehicle and storage medium | |
| CN112163544A (en) | Method and system for judging random placement of non-motor vehicles | |
| CN114926791A (en) | Method and device for detecting abnormal lane change of vehicles at intersection, storage medium and electronic equipment | |
| CN111435445A (en) | Training method and device of character recognition model and character recognition method and device | |
| CN110909674A (en) | Traffic sign identification method, device, equipment and storage medium | |
| US20230401837A1 (en) | Method for training neural network model and method for generating image | |
| CN116824152A (en) | Target detection method and device based on point cloud, readable storage medium and terminal | |
| US20220164584A1 (en) | Method and system for detecting lane pattern | |
| CN115035591A (en) | Dog walking behavior detection method and device | |
| CN111767904A (en) | Traffic incident detection method, device, terminal and storage medium | |
| CN113468938A (en) | Traffic image recognition method and device, image processing equipment and readable storage medium | |
| CN112215042A (en) | Parking space limiter identification method and system and computer equipment | |
| CN112784642B (en) | Vehicle detection method and device | |
| CN117636266B (en) | Method and system for detecting safety behaviors of workers, storage medium and electronic equipment | |
| CN112528910B (en) | Hand-off steering wheel detection method and device, 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 | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20210604 |