CN112989956A - Traffic light identification method and system based on region of interest and storage medium - Google Patents

Traffic light identification method and system based on region of interest and storage medium Download PDF

Info

Publication number
CN112989956A
CN112989956A CN202110193164.0A CN202110193164A CN112989956A CN 112989956 A CN112989956 A CN 112989956A CN 202110193164 A CN202110193164 A CN 202110193164A CN 112989956 A CN112989956 A CN 112989956A
Authority
CN
China
Prior art keywords
traffic light
interest
region
light identification
vanishing point
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Pending
Application number
CN202110193164.0A
Other languages
Chinese (zh)
Inventor
吕轩轩
苑鑫鑫
孙凯信
杨焕利
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Weichai Intelligent Technology Co ltd
Weichai Power Co Ltd
Original Assignee
Weichai Intelligent Technology Co ltd
Weichai Power Co Ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Weichai Intelligent Technology Co ltd, Weichai Power Co Ltd filed Critical Weichai Intelligent Technology Co ltd
Priority to CN202110193164.0A priority Critical patent/CN112989956A/en
Publication of CN112989956A publication Critical patent/CN112989956A/en
Pending legal-status Critical Current

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
    • G06F18/24—Classification techniques
    • G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/04—Architecture, e.g. interconnection topology
    • G06N3/045—Combinations of networks
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/08—Learning methods
    • 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
    • G06V10/40—Extraction of image or video features
    • G06V10/44—Local feature extraction by analysis of parts of the pattern, e.g. by detecting edges, contours, loops, corners, strokes or intersections; Connectivity analysis, e.g. of connected components
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00—Arrangements for image or video recognition or understanding
    • G06V10/40—Extraction of image or video features
    • G06V10/48—Extraction of image or video features by mapping characteristic values of the pattern into a parameter space, e.g. Hough transformation
    • 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
    • G06V20/588—Recognition of the road, e.g. of lane markings; Recognition of the vehicle driving pattern in relation to the road

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Multimedia (AREA)
  • Data Mining & Analysis (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Artificial Intelligence (AREA)
  • General Engineering & Computer Science (AREA)
  • Evolutionary Computation (AREA)
  • Computing Systems (AREA)
  • Biomedical Technology (AREA)
  • General Health & Medical Sciences (AREA)
  • Computational Linguistics (AREA)
  • Biophysics (AREA)
  • Mathematical Physics (AREA)
  • Software Systems (AREA)
  • Molecular Biology (AREA)
  • Health & Medical Sciences (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Evolutionary Biology (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Image Analysis (AREA)
  • Traffic Control Systems (AREA)

Abstract

The application provides a traffic light identification method, a traffic light identification system and a storage medium based on an interested area, wherein the traffic light identification method, the traffic light identification system and the storage medium are used for acquiring an original traffic light image and carrying out gray processing to obtain a gray image; according to the gray images, vanishing point detection is carried out, and the positions of the vanishing points are determined; determining an area of interest according to an area above a horizontal line where the vanishing point is located; and inputting the region of interest into a target detection neural network to obtain a traffic light identification result. The traffic light identification detection method and the traffic light identification detection device have the advantages that the parts above the horizontal line where the vanishing points are located are determined to be the interested areas identified by the traffic light, the traffic light identification detection is carried out on the basis of the interested areas, the false detection rate of the traffic light is greatly reduced, the phenomena of false detection, missing detection and the like caused by the fact that the rear lights of the front vehicle are identified to be red lights and the like are avoided, and further the probability of safety accidents is avoided.

Description

Traffic light identification method and system based on region of interest and storage medium
Technical Field
The application belongs to the technical field of automatic driving, and particularly relates to a traffic light identification method and system based on an interested area and a storage medium.
Background
With the wider application of intelligent technology, the automatic driving technology comes up at the same time, and during automatic driving, the identification of traffic lights has very important influence on automatic driving of vehicles.
The advanced driving assistance system senses the surrounding environment in the driving process of the automobile by using sensors, such as millimeter wave radar, laser radar, a camera and satellite navigation, and collects data, identifies, detects and tracks static and dynamic objects, and performs systematic operation and analysis by combining with navigator map data, so that a driver can predict possible dangers in advance, and the safety is effectively improved. At present, city traffic light recognition based on vision is one of the core contents of auxiliary driving research, and the traffic light state is generally detected and recognized according to certain characteristics of traffic light images, such as color, shape and the like, but the phenomena of false detection and missing detection are very easy to generate when the traffic light is detected by algorithms; in which the rear lights of the front vehicle are easily recognized as red lights, resulting in erroneous decision and control of the driving assistance system, such as unnecessary braking behavior, and even causing serious safety accidents.
Therefore, a traffic light recognition technology applied to the field of safe driving is urgently needed, and the traffic light state can be accurately recognized to ensure the safety of automatic driving.
Disclosure of Invention
The invention provides a traffic light identification method, a traffic light identification system and a storage medium based on an interested area, and aims to solve the problem that the traffic light is identified by using the characteristics of color, shape and the like, so that the phenomena of false detection and missing detection are easily generated, and further serious safety accidents are caused.
According to a first aspect of the embodiments of the present application, a traffic light identification method based on a region of interest is provided, which specifically includes the following steps:
acquiring an original image of a traffic light, and performing graying processing to obtain a grayed image;
according to the gray images, vanishing point detection is carried out, and the positions of the vanishing points are determined;
determining an area of interest according to an area above a horizontal line where the vanishing point is located;
and inputting the region of interest into a target detection neural network to obtain a traffic light identification result.
In some embodiments of the present application, performing vanishing point detection according to a grayed image, and determining a vanishing point position specifically includes:
identifying a plurality of road routes according to the gray-scale image;
and obtaining the intersection point position of the plurality of road routes, namely the vanishing point position according to the plurality of road routes.
In some embodiments of the present application, identifying a plurality of road routes according to the grayed-out image specifically includes: and fitting a plurality of lane lines in the gray image through Sobel edge detection and Hough transform algorithm.
In some embodiments of the present application, obtaining the intersection position of the plurality of road lines, i.e., the vanishing point position, according to the plurality of road lines includes obtaining the intersection position of two road lines, i.e., the vanishing point position, according to the left lane line and the right lane line.
In some embodiments of the present application, the intersection point position of two lane lines is obtained according to a left lane line and a right lane line, and the specific steps include:
obtaining a left lane line image coordinate formula through Hough transformation:
y＝klx+bl；
and a right lane line image coordinate formula:
y＝krx+br；
according to the above formula, the coordinates of the intersection point of the left lane line and the right lane line are obtained as (x,
Figure BDA0002945946360000021
) I.e. the location of the vanishing point;
wherein, (x, y) is the coordinate of each point on the lane line; (k)l,bl) Is a linear coordinate parameter of the left lane line; (k)r,br) As a linear coordinate parameter of the right lane line
In some embodiments of the present application, determining a region of interest according to a region above a horizontal line where a vanishing point is located specifically includes:
determining the horizontal line coordinate of the vanishing point as follows:
Figure BDA0002945946360000022
determining the region of interest as:
Figure BDA0002945946360000023
in some embodiments of the present application, the target detection neural network is a SqueezeDet full convolution neural network.
According to a second aspect of the embodiments of the present application, there is provided a traffic light identification system based on a region of interest, which specifically includes:
a graying image module: the system comprises a display device, a processing device and a processing system, wherein the display device is used for acquiring an original image of a traffic light and carrying out graying processing to obtain a grayed image;
vanishing point detection module: the device is used for detecting a vanishing point according to the gray image and determining the position of the vanishing point;
a region of interest module: the method comprises the steps of determining an area of interest according to an area above a horizontal line where a vanishing point is located;
traffic light identification module: and the method is used for inputting the region of interest into the target detection neural network to obtain a traffic light identification result.
According to a third aspect of the embodiments of the present application, there is provided a traffic light identification device based on a region of interest, including:
a memory: for storing executable instructions; and
and the processor is connected with the memory to execute the executable instructions so as to complete the traffic light identification method based on the region of interest.
According to a fourth aspect of embodiments of the present application, there is provided a computer-readable storage medium having a computer program stored thereon; the computer program is executed by a processor to implement a traffic light identification method based on a region of interest.
By adopting the traffic light identification method, the traffic light identification system and the storage medium based on the region of interest in the embodiment of the application, the original traffic light image is obtained, and the gray level image is obtained by carrying out gray level processing; according to the gray images, vanishing point detection is carried out, and the positions of the vanishing points are determined; determining an area of interest according to an area above a horizontal line where the vanishing point is located; and inputting the region of interest into a target detection neural network to obtain a traffic light identification result. The traffic light identification detection method and the traffic light identification detection device have the advantages that the parts above the horizontal line where the vanishing points are located are determined to be the interested areas identified by the traffic light, the traffic light identification detection is carried out on the basis of the interested areas, the false detection rate of the traffic light is greatly reduced, the phenomena of false detection, missing detection and the like caused by the fact that the rear lights of the front vehicle are identified to be red lights and the like are avoided, and further the probability of safety accidents 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 diagram illustrating steps of a traffic light identification method based on a region of interest according to an embodiment of the present application;
fig. 2 is a flowchart illustrating a traffic light identification method based on a region of interest according to an embodiment of the present application;
fig. 3 is a schematic diagram illustrating the determination of the region of interest in the traffic light identification method according to the embodiment of the present application;
fig. 4 is a schematic diagram illustrating a region of interest determination in a real scene in a traffic light identification method according to an embodiment of the present application;
fig. 5 is a schematic structural diagram illustrating a traffic light identification system based on a region of interest according to an embodiment of the present application;
a schematic structural diagram of a traffic light identification device based on a region of interest according to an embodiment of the present application is shown in fig. 6.
Detailed Description
In the process of realizing the application, the inventor finds that when the existing intelligent driving identifies the traffic lights, the characteristics of the traffic lights such as color and shape are mostly used for identification, so that the phenomena of false detection and missing detection of the red lights and the like of the rear lamps of the front vehicle are easily identified, and further the problem of serious safety accidents is caused.
According to the traffic light identification method and device, the traffic light is generally positioned on the upper half part of the identification image, so that the part above the horizontal line where the vanishing point is positioned is determined as the interested area of the traffic light identification based on the vanishing point detection, the traffic light identification detection is carried out on the basis of the interested area, and the false detection rate of the traffic light can be greatly reduced.
Based on the method, the system and the storage medium for identifying the traffic lights based on the interesting regions, the original traffic light images are obtained, and graying processing is carried out to obtain grayed images; according to the gray images, vanishing point detection is carried out, and the positions of the vanishing points are determined; determining an area of interest according to an area above a horizontal line where the vanishing point is located; and inputting the region of interest into a target detection neural network to obtain a traffic light identification result.
According to the method, the position of the image vanishing point is determined based on edge detection and Hough transformation, the area above the horizontal line of the vanishing point is the interesting area identified by the traffic light, then the traffic light is identified by utilizing the squeezedet detection network, and low-power consumption detection is realized.
The traffic light identification detection is carried out on the basis of the interested areas, the false detection rate of the traffic light is greatly reduced, the phenomena of false detection, missing detection and the like of the red light identified by the rear vehicle light of the front vehicle are avoided, unnecessary braking is avoided, the probability of safety accidents is further avoided, meanwhile, the safety of auxiliary driving is improved, and the user experience is improved.
In order to make the technical solutions and advantages of the embodiments of the present application more apparent, the following further detailed description of the exemplary embodiments of the present application with reference to the accompanying drawings makes it clear that the described embodiments are only a part of the embodiments of the present application, and are not exhaustive of all embodiments. It should be noted that the embodiments and features of the embodiments in the present application may be combined with each other without conflict.
Example 1
Fig. 1 is a schematic diagram illustrating steps of a traffic light identification method based on a region of interest according to an embodiment of the present application. A flow chart of a traffic light identification method based on a region of interest according to an embodiment of the present application is shown in fig. 2.
As shown in fig. 1 and fig. 2, the traffic light identification method based on the region of interest according to the embodiment of the present application specifically includes the following steps:
s101: and acquiring an original image of the traffic light, and performing gray processing to obtain a gray image.
Specifically, the gray level image obtained by carrying out gray level processing on the original image of the traffic light contains a lot of noise, and the median filtering algorithm is used for carrying out smooth noise reduction on the image, so that interference information of subsequent processing can be reduced.
S102: and according to the gray images, carrying out vanishing point detection and determining the positions of the vanishing points.
S103: and determining the area as the interested area according to the area above the horizontal line where the vanishing point is positioned.
Specifically, firstly, a plurality of road routes are identified according to the gray-scale image; then, according to the multiple road routes, the intersection point position of the multiple road routes, namely the vanishing point position, is obtained.
The method for recognizing the multiple road routes according to the gray-scale image specifically comprises the following steps: and fitting a plurality of lane lines in the gray image through Sobel edge detection and Hough transform algorithm.
According to the method, Sobel edge detection is carried out on the image after graying, then straight line detection is carried out by utilizing Hough transform algorithm (Hough), and a lane line on the lane image is fitted; the Hough transform algorithm can convert a straight line in an image coordinate system into a point in a parameter coordinate system, and the equation of the parameter coordinate system is as follows: ρ is xcos θ + ysin θ.
Because all the lane lines can be intersected at the vanishing point, after the vanishing point is determined, the position above the horizontal line where the lane lines are located is the interesting area identified by the traffic light.
Theoretically, two straight lines can determine an intersection point, and the plurality of lane lines at least comprise a left lane line and a right lane line. Therefore, the present application further describes the determination process of the region of interest roi (region of interest) with two lane lines, left and right.
Fig. 3 is a schematic diagram illustrating the determination of the region of interest in the traffic light identification method according to the embodiment of the present application. Fig. 4 is a schematic diagram illustrating a region of interest determination in a real scene in a traffic light identification method according to an embodiment of the present application.
As shown in fig. 3 and 4, the position of the intersection O of the two road lines, i.e., the vanishing point position, is calculated from the left lane line a and the right lane line B. And then determining a region of interest ROI (region of interest) according to the horizontal line where the vanishing point is located.
The method comprises the following specific steps:
1) obtaining a left lane line A image coordinate formula (1) through Hough transformation:
y＝klx+bl(ii) a Formula (1)
And right lane line B image coordinate formula (2):
y＝krx+br(ii) a Formula (2)
According to the above formulas (1) and (2), the left lane line is obtainedThe coordinates of the intersection O with the right lane line are (x,
Figure BDA0002945946360000051
) I.e. the location of the vanishing point;
wherein, (x, y) is the coordinate of each point on the lane line; (k)l,bl) Is a linear coordinate parameter of the left lane line; (k)r,br) Is a straight line coordinate parameter of the right lane line.
2) Determining an area of interest according to an area above a horizontal line where the vanishing point is located, and specifically comprising the following steps:
determining the horizontal line coordinate of the vanishing point O as follows:
Figure BDA0002945946360000061
determining the range of the region of interest ROI as follows:
Figure BDA0002945946360000062
s104: and inputting the region of interest into a target detection neural network to obtain a traffic light identification result.
Specifically, the target detection neural network is an SqueezeDet full convolution neural network.
The SqueezeDet is a small-sized, low-power-consumption full convolution neural network applied to real-time target detection in the field of automatic driving. And after the image interesting area is determined, transmitting the image to a SqueezeDet target detection network for detecting traffic lights.
By adopting the traffic light identification method based on the region of interest in the embodiment of the application, the original traffic light image is obtained, and the gray level processing is carried out to obtain the gray level image; according to the gray images, vanishing point detection is carried out, and the positions of the vanishing points are determined; determining an area of interest according to an area above a horizontal line where the vanishing point is located; and inputting the region of interest into a target detection neural network to obtain a traffic light identification result.
According to the method, the position of the image vanishing point is determined based on edge detection and Hough transformation, the area above the horizontal line of the vanishing point is the interesting area identified by the traffic light, then the traffic light is identified by utilizing the squeezedet detection network, and low-power consumption detection is realized.
The traffic light identification detection is carried out on the basis of the interested areas, the false detection rate of the traffic light is greatly reduced, the phenomena of false detection, missing detection and the like of the red light identified by the rear vehicle light of the front vehicle are avoided, unnecessary braking is avoided, the probability of safety accidents is further avoided, meanwhile, the safety of auxiliary driving is improved, and the user experience is improved.
Example 2
For details not disclosed in the traffic light identification system based on the region of interest of this embodiment, please refer to specific implementation contents of the traffic light identification method based on the region of interest in other embodiments.
A schematic structural diagram of a traffic light identification system based on a region of interest according to an embodiment of the present application is shown in fig. 5.
As shown in fig. 5, the traffic light identification system based on a region of interest according to the embodiment of the present application specifically includes a grayscale image module 10, a vanishing point detecting module 20, a region of interest module 30, and a traffic light identification module 40.
In particular, the method comprises the following steps of,
graying image module 10: the method is used for acquiring the original image of the traffic light and carrying out gray processing to obtain a gray image.
Specifically, the gray level image obtained by carrying out gray level processing on the original image of the traffic light contains a lot of noise, and the median filtering algorithm is used for carrying out smooth noise reduction on the image, so that interference information of subsequent processing can be reduced.
Vanishing point detecting module 20: and the method is used for detecting the vanishing point according to the gray images and determining the vanishing point position.
Region of interest module 30: and determining the area as the region of interest according to the area above the horizontal line where the vanishing point is located.
Specifically, firstly, a plurality of road routes are identified according to the gray-scale image; then, according to the multiple road routes, the intersection point position of the multiple road routes, namely the vanishing point position, is obtained.
The method for recognizing the multiple road routes according to the gray-scale image specifically comprises the following steps: and fitting a plurality of lane lines in the gray image through Sobel edge detection and Hough transform algorithm.
According to the method, Sobel edge detection is carried out on the image after graying, then straight line detection is carried out by utilizing Hough transform algorithm (Hough), and a lane line on the lane image is fitted; the Hough transform algorithm can convert a straight line in an image coordinate system into a point in a parameter coordinate system, and the equation of the parameter coordinate system is as follows: ρ is x cos θ + y sin θ.
Theoretically, two straight lines can determine an intersection point, and the plurality of lane lines at least comprise a left lane line and a right lane line. Therefore, the present application further describes the determination process of the region of interest roi (region of interest) with two lane lines, left and right.
As shown in fig. 3 and 4, the position of the intersection O of the two road lines, i.e., the vanishing point position, is calculated from the left lane line a and the right lane line B. And then determining a region of interest ROI (region of interest) according to the horizontal line where the vanishing point is located.
The method comprises the following specific steps:
1) obtaining a left lane line A image coordinate formula (1) through Hough transformation:
y＝klx+bl(ii) a Formula (1)
And right lane line B image coordinate formula (2):
y＝krx+br(ii) a Formula (2)
According to the above formulas (1) and (2), the coordinates of the intersection O of the left lane line and the right lane line are obtained as (x,
Figure BDA0002945946360000071
) I.e. the vanishing point location.
Wherein, (x, y) is the coordinate of each point on the lane line; (k)l,bl) Is a linear coordinate parameter of the left lane line; (k)r,br) Is a straight line coordinate parameter of the right lane line.
2) Determining an area of interest according to an area above a horizontal line where the vanishing point is located, and specifically comprising the following steps:
determining the horizontal line coordinate of the vanishing point O as follows:
Figure BDA0002945946360000072
determining the range of the region of interest ROI as follows:
Figure BDA0002945946360000081
the traffic light recognition module 40: and the method is used for inputting the region of interest into the target detection neural network to obtain a traffic light identification result.
Specifically, the target detection neural network is an SqueezeDet full convolution neural network.
The SqueezeDet is a small-sized, low-power-consumption full convolution neural network applied to real-time target detection in the field of automatic driving. And after the image interesting area is determined, transmitting the image to a SqueezeDet target detection network for detecting traffic lights.
By adopting the traffic light identification method based on the region of interest in the embodiment of the application, the gray-scale image module 10 acquires the original traffic light image, and performs gray-scale processing to obtain a gray-scale image; the vanishing point detecting module 20 detects vanishing points according to the gray images to determine the positions of the vanishing points; the region-of-interest module 30 determines a region to be a region of interest according to a region above the horizontal line where the vanishing point is located; the traffic light recognition module 40 inputs the region of interest into the target detection neural network to obtain a traffic light recognition result.
According to the method, the position of the image vanishing point is determined based on edge detection and Hough transformation, the area above the horizontal line of the vanishing point is the interesting area identified by the traffic light, then the traffic light is identified by utilizing the squeezedet detection network, and low-power consumption detection is realized.
The traffic light identification detection is carried out on the basis of the interested areas, the false detection rate of the traffic light is greatly reduced, the phenomena of false detection, missing detection and the like of the red light identified by the rear vehicle light of the front vehicle are avoided, unnecessary braking is avoided, the probability of safety accidents is further avoided, meanwhile, the safety of auxiliary driving is improved, and the user experience is improved.
Example 3
For details that are not disclosed in the traffic light identification device based on the region of interest of this embodiment, please refer to specific implementation contents of the traffic light identification method or system based on the region of interest in other embodiments.
A schematic structural diagram of a traffic light identification device 400 based on a region of interest according to an embodiment of the present application is shown in fig. 3.
As shown in fig. 3, the traffic light identifying apparatus 400 based on the region of interest includes:
the memory 402: for storing executable instructions; and
a processor 401 is coupled to the memory 402 to execute executable instructions to perform the motion vector prediction method.
It will be understood by those skilled in the art that the schematic diagram of fig. 3 is merely an example of the traffic light identification device 400, and does not constitute a limitation on the traffic light identification device 400, and may include more or less components than those shown, or combine some components, or different components, for example, the traffic light identification device 400 may further include input and output devices, network access devices, buses, etc.
The Processor 401 (CPU) may be other general-purpose Processor, a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), a Field-Programmable Gate Array (FPGA) or other Programmable logic device, a discrete Gate or transistor logic device, a discrete hardware component, or the like. The general purpose processor may be a microprocessor or the processor 401 may be any conventional processor or the like, and the processor 401 is a control center of the traffic light identification device 400 and connects the various parts of the entire traffic light identification device 400 using various interfaces and lines.
The memory 402 may be used to store computer readable instructions and the processor 401 may implement the various functions of the traffic light identification device 400 by executing or executing computer readable instructions or modules stored in the memory 402 and invoking data stored in the memory 402. The memory 402 may mainly include a program storage area and a data storage area, wherein the program storage area may store an operating system, an application program required by at least one function (such as a sound playing function, an image playing function, etc.), and the like; the storage data area may store data created according to the traffic light recognition apparatus 400 use, and the like. In addition, the Memory 402 may include a hard disk, a Memory, a plug-in hard disk, a Smart Media Card (SMC), a Secure Digital (SD) Card, a Flash Memory Card (Flash Card), at least one disk storage device, a Flash Memory device, a Read-Only Memory (ROM), a Random Access Memory (RAM), or other non-volatile/volatile storage devices.
The integrated modules of the traffic light recognition device 400, if implemented in the form of software functional modules and sold or used as separate products, may be stored in a computer-readable storage medium. Based on such understanding, all or part of the flow of the method according to the embodiments of the present invention may also be implemented by hardware related to computer readable instructions, which may be stored in a computer readable storage medium, and when the computer readable instructions are executed by a processor, the steps of the method embodiments may be implemented.
Example 4
The present embodiment provides a computer-readable storage medium having stored thereon a computer program; the computer program is executed by a processor to implement the region of interest based traffic light identification method in other embodiments.
The traffic light identification device based on the interesting region and the computer storage medium in the embodiment of the application acquire the original traffic light image, and perform graying processing to obtain a grayed image; according to the gray images, vanishing point detection is carried out, and the positions of the vanishing points are determined; determining an area of interest according to an area above a horizontal line where the vanishing point is located; and inputting the region of interest into a target detection neural network to obtain a traffic light identification result.
According to the method, the position of the image vanishing point is determined based on edge detection and Hough transformation, the area above the horizontal line of the vanishing point is the interesting area identified by the traffic light, then the traffic light is identified by utilizing the squeezedet detection network, and low-power consumption detection is realized.
The traffic light identification detection is carried out on the basis of the interested areas, the false detection rate of the traffic light is greatly reduced, the phenomena of false detection, missing detection and the like of the red light identified by the rear vehicle light of the front vehicle are avoided, unnecessary braking is avoided, the probability of safety accidents is further avoided, meanwhile, the safety of auxiliary driving is improved, and the user experience is improved.
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 present application is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the application. 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.
The terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the invention. As used in this specification and the appended claims, the singular forms "a", "an", and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise. It should also be understood that the term "and/or" as used herein refers to and encompasses any and all possible combinations of one or more of the associated listed items.
It is to be understood that although the terms first, second, third, etc. may be used herein to describe various information, these information should not be limited to these terms. These terms are only used to distinguish one type of information from another. For example, first information may also be referred to as second information, and similarly, second information may also be referred to as first information, without departing from the scope of the present invention. The word "if" as used herein may be interpreted as "at … …" or "when … …" or "in response to a determination", depending on the context.
While the preferred embodiments of the present application have been described, additional variations and modifications in those embodiments may occur to those skilled in the art once they learn of the basic inventive concepts. Therefore, it is intended that the appended claims be interpreted as including preferred embodiments and all alterations and modifications as fall within the scope of the application.
It will be apparent to those skilled in the art that various changes and modifications may be made in the present application without departing from the spirit and scope of the application. Thus, if such modifications and variations of the present application fall within the scope of the claims of the present application and their equivalents, the present application is intended to include such modifications and variations as well.

Claims (10)

1. A traffic light identification method based on an interested area specifically comprises the following steps:
acquiring an original image of a traffic light, and performing graying processing to obtain a grayed image;
according to the gray image, performing vanishing point detection to determine the position of a vanishing point;
determining an area of interest according to an area above a horizontal line where the vanishing point is located;
and inputting the region of interest into a target detection neural network to obtain a traffic light identification result.
2. The traffic light identification method based on the region of interest according to claim 1, wherein the detecting of the vanishing point according to the grayed image and the determining of the vanishing point position specifically comprise:
identifying a plurality of road routes according to the gray-scale image;
and obtaining the intersection point position of the plurality of road routes, namely the vanishing point position according to the plurality of road routes.
3. The traffic light identification method based on the region of interest according to claim 2, wherein the identifying a plurality of road routes according to the grayed images specifically comprises: and fitting a plurality of lane lines in the gray image through Sobel edge detection and Hough transform algorithm.
4. The method of claim 2, wherein obtaining the intersection position (i.e., the vanishing point position) of the plurality of road lines according to the plurality of road lines comprises obtaining the intersection position (i.e., the vanishing point position) of the two road lines according to a left road line and a right road line.
5. The traffic light identification method based on the interested area according to claim 4, wherein the intersection position of the two road lines is obtained according to the left lane line and the right lane line, and the specific steps comprise:
obtaining a left lane line image coordinate formula through Hough transformation:
y＝klx+bl；
and a right lane line image coordinate formula:
y＝krx+br；
according to the formula, the coordinates of the intersection point of the left lane line and the right lane line are obtained as
Figure FDA0002945946350000011
Namely the position of a vanishing point;
wherein, (x, y) is the coordinate of each point on the lane line; (k)l,bl) Is a linear coordinate parameter of the left lane line; (k)r,br) Is a straight line coordinate parameter of the right lane line.
6. The traffic light identification method based on a region of interest according to claim 5, wherein the determining as the region of interest according to the region above the horizontal line where the vanishing point is located specifically comprises:
determining the horizontal line coordinate of the vanishing point as follows:
Figure FDA0002945946350000021
determining the region of interest as:
Figure FDA0002945946350000022
7. the traffic light identification method based on the interested region according to claim 1, characterized in that the target detection neural network is a SqueezeDet full convolution neural network.
8. A traffic light identification system based on a region of interest is characterized by specifically comprising:
a graying image module: the system comprises a display device, a processing device and a processing system, wherein the display device is used for acquiring an original image of a traffic light and carrying out graying processing to obtain a grayed image;
vanishing point detection module: the system is used for detecting a vanishing point according to the grayed image and determining the position of the vanishing point;
a region of interest module: the device is used for determining an area of interest according to an area above a horizontal line where the vanishing point is located;
traffic light identification module: and the area of interest is input into a target detection neural network to obtain a traffic light identification result.
9. A traffic light identification device based on a region of interest, comprising:
a memory: for storing executable instructions; and
a processor for connecting with the memory to execute the executable instructions to complete the region of interest based traffic light identification method of any one of claims 1-7.
10. A computer-readable storage medium, having stored thereon a computer program; a computer program for execution by a processor for implementing a method of traffic light identification based on a region of interest according to any of claims 1-7.
CN202110193164.0A 2021-02-20 2021-02-20 Traffic light identification method and system based on region of interest and storage medium Pending CN112989956A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202110193164.0A CN112989956A (en) 2021-02-20 2021-02-20 Traffic light identification method and system based on region of interest and storage medium

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202110193164.0A CN112989956A (en) 2021-02-20 2021-02-20 Traffic light identification method and system based on region of interest and storage medium

Publications (1)

Publication Number Publication Date
CN112989956A true CN112989956A (en) 2021-06-18

Family

ID=76393761

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202110193164.0A Pending CN112989956A (en) 2021-02-20 2021-02-20 Traffic light identification method and system based on region of interest and storage medium

Country Status (1)

Country Link
CN (1) CN112989956A (en)

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113361453A (en) * 2021-06-25 2021-09-07 东风汽车集团股份有限公司 Traffic light identification system and method under visual fuzzy scene
CN114998867A (en) * 2022-06-27 2022-09-02 安徽酷哇机器人有限公司 Traffic light state detection method and system based on single camera

Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103310006A (en) * 2013-06-28 2013-09-18 电子科技大学 ROI extraction method in auxiliary vehicle driving system
CN103617412A (en) * 2013-10-31 2014-03-05 电子科技大学 Real-time lane line detection method
CN111191482A (en) * 2018-11-14 2020-05-22 杭州海康威视数字技术股份有限公司 Brake lamp identification method and device and electronic equipment
CN111428663A (en) * 2020-03-30 2020-07-17 北京百度网讯科技有限公司 Traffic light state identification method and device, electronic equipment and storage medium
CN111950491A (en) * 2020-08-19 2020-11-17 成都飞英思特科技有限公司 Personnel density monitoring method and device and computer readable storage medium
CN112150560A (en) * 2020-09-27 2020-12-29 上海高德威智能交通系统有限公司 Method and device for determining vanishing point and computer storage medium
CN112364869A (en) * 2021-01-14 2021-02-12 北京经纬恒润科技股份有限公司 Lane line identification method and device

Patent Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103310006A (en) * 2013-06-28 2013-09-18 电子科技大学 ROI extraction method in auxiliary vehicle driving system
CN103617412A (en) * 2013-10-31 2014-03-05 电子科技大学 Real-time lane line detection method
CN111191482A (en) * 2018-11-14 2020-05-22 杭州海康威视数字技术股份有限公司 Brake lamp identification method and device and electronic equipment
CN111428663A (en) * 2020-03-30 2020-07-17 北京百度网讯科技有限公司 Traffic light state identification method and device, electronic equipment and storage medium
CN111950491A (en) * 2020-08-19 2020-11-17 成都飞英思特科技有限公司 Personnel density monitoring method and device and computer readable storage medium
CN112150560A (en) * 2020-09-27 2020-12-29 上海高德威智能交通系统有限公司 Method and device for determining vanishing point and computer storage medium
CN112364869A (en) * 2021-01-14 2021-02-12 北京经纬恒润科技股份有限公司 Lane line identification method and device

Non-Patent Citations (2)

* Cited by examiner, † Cited by third party
Title
BICHEN WU等: "SqueezeDet: Unified, Small, Low Power Fully Convolutional Neural Networks for Real-Time Object Detection for Autonomous Driving", 《2017 IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION WORKSHOPS (CVPRW)》 *
上海市交通电子行业协会编: "《上海交通电子产业创新研究》", 31 August 2016 *

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113361453A (en) * 2021-06-25 2021-09-07 东风汽车集团股份有限公司 Traffic light identification system and method under visual fuzzy scene
CN114998867A (en) * 2022-06-27 2022-09-02 安徽酷哇机器人有限公司 Traffic light state detection method and system based on single camera

Similar Documents

Publication Publication Date Title
Andrade et al. A novel strategy for road lane detection and tracking based on a vehicle’s forward monocular camera
Suhr et al. Automatic parking space detection and tracking for underground and indoor environments
Rezaei et al. Robust vehicle detection and distance estimation under challenging lighting conditions
JP5690688B2 (en) Outside world recognition method, apparatus, and vehicle system
Suhr et al. Sensor fusion-based vacant parking slot detection and tracking
CN113744560B (en) Automatic parking method and device for parking lot, server and machine-readable storage medium
US8184159B2 (en) Forward looking sensor system
CN110929655B (en) Lane line identification method in driving process, terminal device and storage medium
US20150161796A1 (en) Method and device for recognizing pedestrian and vehicle supporting the same
US20130211682A1 (en) System and method for traffic signal recognition
US8050460B2 (en) Method for recognition of an object
JP2024023319A (en) Detection of emergency vehicle
US20230184560A1 (en) Visual interface display method and apparatus, electronic device, and storage medium
CN112989956A (en) Traffic light identification method and system based on region of interest and storage medium
Em et al. Vision-based lane departure warning framework
CN114684062A (en) Restraint device positioning
CN113787997A (en) Emergency braking control method, electronic device, and storage medium
Kim et al. An intelligent and integrated driver assistance system for increased safety and convenience based on all-around sensing
EP4113377A1 (en) Use of dbscan for lane detection
CN118107563A (en) Parking control method and device for vehicle and storage medium
CN113920490A (en) Vehicle obstacle detection method, device and equipment
JP6861911B2 (en) Information processing equipment, information processing methods and information processing programs
JP2015001966A (en) Object detection device
KR20180069282A (en) Method of detecting traffic lane for automated driving
EP3002708A1 (en) Perspective transform of mono-vision image

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