CN113361303A - Temporary traffic sign board identification method, device and equipment - Google Patents
Temporary traffic sign board identification method, device and equipment Download PDFInfo
- Publication number
- CN113361303A CN113361303A CN202010148754.7A CN202010148754A CN113361303A CN 113361303 A CN113361303 A CN 113361303A CN 202010148754 A CN202010148754 A CN 202010148754A CN 113361303 A CN113361303 A CN 113361303A
- Authority
- CN
- China
- Prior art keywords
- signboard
- area
- target
- traffic sign
- 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.)
- Granted
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/22—Matching criteria, e.g. proximity measures
Landscapes
- Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Traffic Control Systems (AREA)
- Image Analysis (AREA)
Abstract
The application provides a temporary traffic sign board identification method, a device and equipment, which relate to the field of artificial intelligence, and the specific implementation scheme is as follows: acquiring a target road image containing a traffic sign and detecting a sign area in the road image; extracting the sign information in the sign board area, matching the sign information with preset target information, and if the matching fails, performing pixel semantic segmentation processing on the road image to obtain one or more reference areas; determining a target area and a corresponding target area type from one or more reference areas, and acquiring a target strategy corresponding to the target area type; and analyzing the position relation between the signboard area and the target area according to a target strategy to determine whether the traffic signboard is a temporary traffic signboard. Therefore, the temporary traffic sign can be identified based on the position relation between the sign and the target area, and the identification efficiency and accuracy are improved.
Description
Technical Field
The application relates to the technical field of computers, in particular to the technical field of artificial intelligence, and provides a temporary traffic sign board identification method, device and equipment.
Background
With the development of intelligent automobiles and automatic driving technologies, traffic signs play a vital role in safe driving. In daily life, temporary traffic signboards are very common, and for example, temporary traffic signboards are usually set for scenes such as temporary construction and speed limit, so that in order to enrich map data, a user is reminded to avoid temporary roadblocks or slow down during vehicle running, user experience is improved, and the recognition of the temporary traffic signboards is of great significance.
Currently, a scheme for quickly and accurately identifying temporary traffic signs is needed.
Disclosure of Invention
The present application is directed to solving, at least to some extent, one of the technical problems in the related art.
Therefore, a first objective of the present application is to provide a temporary traffic sign recognition method, so as to realize recognition of the temporary traffic sign, and improve recognition efficiency and accuracy.
A second object of the present application is to provide a temporary traffic sign recognition apparatus.
A third object of the present application is to provide an electronic device.
A fourth object of the present application is to propose a computer readable storage medium.
An embodiment of a first aspect of the present application provides a temporary traffic sign identification method, including:
acquiring a target road image containing a traffic sign, and detecting a sign area in the target road image;
extracting the sign information in the sign board area, matching the sign information with preset target information, and if the matching fails, performing pixel semantic segmentation processing on the target road image to obtain one or more reference areas;
determining a target area and a corresponding target area type from the one or more reference areas, and acquiring a target strategy corresponding to the target area type;
and analyzing the position relation between the signboard area and the target area according to the target strategy to determine whether the traffic signboard is a temporary traffic signboard.
In addition, the temporary traffic sign recognition method according to the above-described embodiment of the present application may further have the following additional technical features:
optionally, the acquiring the target road image containing the traffic sign board comprises: shooting a road image sequence which comprises a traffic signboard and is marked with a shooting position; and determining the target road image from the road image sequence according to the distance change of the shooting position and the area size change of the traffic signboard on the image.
Optionally, the type of the target area is a road surface, and the analyzing the position relationship between the signboard area and the target area according to the target policy to determine whether the traffic signboard is a temporary traffic signboard includes: judging whether the signboard region and the road surface region have an overlapping region, if so, determining that the traffic signboard is a temporary traffic signboard, and if not, judging whether the distance between the signboard region and the road surface region is smaller than a preset threshold value; and if the distance is smaller than the preset threshold value, determining that the traffic sign board is a temporary traffic sign board.
Optionally, the type of the target area is a fence, and the analyzing the position relationship between the signboard area and the target area according to the target policy to determine whether the traffic signboard is a temporary traffic signboard includes: judging whether the distance between the signboard area and the fence area is smaller than a preset threshold value or not; if the distance is smaller than the preset threshold value, determining that the traffic sign board is a temporary traffic sign board; if the distance is not smaller than the preset threshold value, judging whether the height of the signboard area is lower than that of the fence area; if yes, determining that the traffic sign board is a temporary traffic sign board.
Optionally, the type of the target area is a vehicle, and the analyzing the position relationship between the signboard area and the target area according to the target policy to determine whether the traffic signboard is a temporary traffic signboard includes: judging whether the signboard area and the vehicle area have an overlapping area; and if the overlapped area is determined to exist, determining that the traffic sign board is a temporary traffic sign board.
Optionally, after matching the flag information with preset target information, the method further includes: and if the matching is successful, determining that the traffic sign board is a temporary traffic sign board.
An embodiment of a second aspect of the present application provides a temporary traffic sign recognition apparatus, including:
the system comprises an acquisition module, a display module and a display module, wherein the acquisition module is used for acquiring a target road image containing a traffic sign and detecting a sign area in the target road image;
the processing module is used for extracting the sign information in the sign board area, matching the sign information with preset target information, and if the matching fails, performing pixel semantic segmentation processing on the target road image to acquire one or more reference areas;
the determining module is used for determining a target area and a corresponding target area type from the one or more reference areas and acquiring a target strategy corresponding to the target area type;
and the identification module is used for analyzing the position relation between the signboard area and the target area according to the target strategy and determining whether the traffic signboard is a temporary traffic signboard.
In addition, the temporary traffic sign recognition apparatus according to the above-described embodiment of the present application may further have the following additional technical features:
optionally, the obtaining module is specifically configured to: shooting a road image sequence which comprises a traffic signboard and is marked with a shooting position; and determining the target road image from the road image sequence according to the distance change of the shooting position and the area size change of the traffic signboard on the image.
Optionally, the type of the target area is a road surface, and the identification module is specifically configured to: judging whether the signboard region and the road surface region have an overlapping region, if so, determining that the traffic signboard is a temporary traffic signboard, and if not, judging whether the distance between the signboard region and the road surface region is smaller than a preset threshold value; and if the distance is smaller than the preset threshold value, determining that the traffic sign board is a temporary traffic sign board.
Optionally, the type of the target area is a fence, and the identification module is specifically configured to: judging whether the distance between the signboard area and the fence area is smaller than a preset threshold value or not; if the distance is smaller than the preset threshold value, determining that the traffic sign board is a temporary traffic sign board; if the distance is not smaller than the preset threshold value, judging whether the height of the signboard area is lower than that of the fence area; if yes, determining that the traffic sign board is a temporary traffic sign board.
Optionally, the type of the target area is a vehicle, and the identification module is specifically configured to: judging whether the signboard area and the vehicle area have an overlapping area; and if the overlapped area is determined to exist, determining that the traffic sign board is a temporary traffic sign board.
Optionally, the apparatus further comprises: and the matching determination module is used for determining that the traffic sign board is a temporary traffic sign board if the matching is successful.
The embodiment of the third aspect of the present application provides an electronic device, which includes at least one processor, and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor to enable the at least one processor to perform the temporary traffic sign recognition method according to the embodiment of the first aspect.
An embodiment of a fourth aspect of the present application provides a non-transitory computer-readable storage medium storing computer instructions for causing a computer to execute the temporary traffic sign recognition method according to the embodiment of the first aspect.
One embodiment in the above application has the following advantages or benefits: the method comprises the steps of acquiring a target road image containing a traffic sign, and detecting a sign area in the road image. And further extracting the mark information in the signboard area, matching the mark information with preset target information, and if the matching fails, performing pixel semantic segmentation processing on the road image to acquire one or more reference areas. Further, a target area and a corresponding target area type are determined from one or more reference areas, a target strategy corresponding to the target area type is obtained, and the position relation between the signboard area and the target area is analyzed according to the target strategy to determine whether the traffic signboard is a temporary traffic signboard. Therefore, the temporary traffic sign can be identified based on the position relation between the sign and the target area, and the identification efficiency and accuracy are improved.
Other effects of the above-described alternative will be described below with reference to specific embodiments.
Drawings
The drawings are included to provide a better understanding of the present solution and are not intended to limit the present application. Wherein:
fig. 1 is a schematic flow chart of a temporary traffic sign recognition method according to an embodiment of the present disclosure;
FIG. 2 is a schematic flow chart illustrating another temporary traffic sign identification method according to an embodiment of the present disclosure;
FIG. 3 is a schematic flow chart illustrating another temporary traffic sign identification method according to an embodiment of the present disclosure;
FIG. 4 is a schematic diagram of a semantically segmented image;
fig. 5 is a schematic structural diagram of a temporary traffic sign recognition apparatus according to an embodiment of the present disclosure;
fig. 6 is a schematic structural diagram of another temporary traffic sign recognition apparatus according to an embodiment of the present disclosure;
FIG. 7 illustrates a block diagram of an exemplary electronic device suitable for use in implementing embodiments of the present application.
Detailed Description
The following description of the exemplary embodiments of the present application, taken in conjunction with the accompanying drawings, includes various details of the embodiments of the application for the understanding of the same, which are to be considered exemplary only. Accordingly, those of ordinary skill in the art will recognize that various changes and modifications of the embodiments described herein can be made without departing from the scope and spirit of the present application. Also, descriptions of well-known functions and constructions are omitted in the following description for clarity and conciseness.
Fig. 1 is a schematic flow chart of a temporary traffic sign identification method according to an embodiment of the present application, and as shown in fig. 1, the method includes:
In practical application, construction, speed limit and other scenes which temporarily influence road traffic are quite common, temporary traffic signboards are usually set in the scenes, and in order to enrich map data, a user is reminded to avoid temporary roadblocks or slow down during vehicle running and improve user experience, a method capable of identifying the temporary traffic signboards is needed.
In this embodiment, when the temporary traffic sign is recognized, a target road image including the traffic sign may be acquired, and a sign area in the target road image may be detected. The target road image may be one frame or multiple frames, which is not limited herein.
As an example, a target road image including a traffic sign is acquired by an image acquisition device, and the target road image is recognized according to a pre-trained object detection model, so as to acquire a sign area in the target road image. The object detection model can be obtained by training the sample image through a correlation technique, and details are not repeated here.
It should be noted that the above implementation manner is only an example, and the signboard region in the target road image may be obtained through image semantic segmentation, or the like, and the region obtained by the object detection model may be merged with the region obtained by semantic segmentation to obtain the signboard region, so as to avoid inaccurate detection in a single manner, which is not limited herein.
And 102, extracting the sign information in the sign board area, matching the sign information with preset target information, and if the matching fails, performing pixel semantic segmentation processing on the target road image to acquire one or more reference areas.
In this embodiment, character recognition may be performed on the image of the signboard region, and the sign information in the signboard region may be extracted. Presetting a keyword table of the temporary traffic sign board, matching the extracted identification information with target information in the keyword table, and if the matching fails, performing pixel semantic segmentation processing on the road image to obtain one or more reference areas.
The reference area includes, but is not limited to, a road surface area, a fence area, a vehicle area, a sky area, a green belt area, and the like.
In one embodiment of the present application, if the matching is successful, the traffic sign is determined to be a temporary traffic sign.
As an example, the keyword table includes construction, and if the image of the signboard region is subjected to character recognition to obtain the content of the signboard, which includes "construction", it is determined that the matching is successful, and the traffic signboard is determined to be a temporary traffic signboard. Otherwise, determining that the matching fails, and performing pixel semantic segmentation processing on the road image to acquire one or more reference areas.
In this embodiment, when performing pixel semantic segmentation processing on a road image to obtain one or more reference areas, the type of each reference area may also be determined, and then, according to the set type of the target area, the target area is determined by combining the type of each reference area.
As an example, the target area type includes a road surface, a fence, and a vehicle, and the road surface area, the fence area, and the vehicle area are acquired from the reference area as the target area.
For different types of areas, different target strategies can be set, so that the position relation between the signboard area and the target area is analyzed according to the target strategies, and whether the traffic signboard is a temporary traffic signboard or not is determined according to the position relation.
And 104, analyzing the position relation between the signboard area and the target area according to a target strategy to determine whether the traffic signboard is a temporary traffic signboard.
In this embodiment, the position relationship between the signboard region and the target region is analyzed, and whether the traffic signboard is a temporary traffic signboard is determined according to the analysis result. Because the temporary traffic sign board is often placed on a road and can move, the height of the sign board is low, and the like, whether the traffic sign board meets the characteristics or not is judged by analyzing the position relation between the area of the sign board and the surrounding environment area, and therefore whether the traffic sign board is the temporary traffic sign board or not is determined.
There are various ways of analyzing the position relationship between the signboard region and the target region to determine whether the traffic signboard is a temporary traffic signboard, which are described below.
In one embodiment of the present application, if the target area is a road surface area, the position relationship between the signboard area and the road surface area is analyzed according to a strategy corresponding to the road surface area to determine whether the target area is a temporary traffic signboard.
As an example, it is determined whether the signboard region and the road surface region have an overlapping region, and if it is determined that there is an overlapping region, it is determined that the traffic signboard is a temporary traffic signboard, and if it is determined that there is no overlapping region, it is determined that there is no temporary traffic signboard. If the signboard region and the road surface region have an overlapping region, the scene where the traffic signboard is placed on the road surface is determined, and thus the temporary traffic signboard is determined.
As another example, further, after it is determined that the signboard region and the road surface region do not have an overlapping region, the distance between the signboard region and the road surface region may be obtained, and it is determined whether the distance between the signboard region and the road surface region is smaller than a preset threshold value; and if the distance is smaller than the preset threshold value, determining that the traffic sign board is a temporary traffic sign board. Wherein obtaining the distance between the sign area and the road surface area comprises, for example: and taking the minimum value of the distance between each pixel point in the signboard area and each pixel point in the road surface area as the distance between the signboard area and the road surface area. In this example, if the distance between the judgment areas is less than the preset threshold, it is judged that the traffic signboard is set on the road surface, and thus it is determined to be a temporary traffic signboard.
In one embodiment of the present application, if the target area is a fence area, the position relationship between the signboard area and the fence area is analyzed according to a strategy corresponding to the fence area to determine whether the traffic signboard is a temporary traffic signboard.
As an example, whether the distance between the signboard region and the barrier region is smaller than a preset threshold is determined, if the distance is smaller than the preset threshold, the traffic signboard is determined to be a temporary traffic signboard, and if the distance is not smaller than the preset threshold, the traffic signboard is determined not to be the temporary traffic signboard. If the distance between the signboard area and the fence area is short, the situation that the traffic signboard is arranged on the fence is judged, and therefore the temporary traffic signboard is determined.
As another example, after it is known that the distance is not less than the preset threshold, it may be further determined whether the height of the signboard region is lower than the height of the fence region, if so, it is determined that the traffic signboard is a temporary traffic signboard, and if not, it is determined that the traffic signboard is not the temporary traffic signboard. The temporary traffic sign is determined by judging whether the traffic sign is hung under the fence or not and if the traffic sign is hung under the fence.
In one embodiment of the present application, if the target area is a vehicle area, the position relationship between the signboard area and the vehicle area is analyzed according to a strategy corresponding to the vehicle area to determine whether the target area is a temporary traffic signboard.
As an example, it is determined whether the sign area and the vehicle area have an overlapping area; and if the overlapped area is determined to exist, determining the traffic sign board as a temporary traffic sign board. Wherein, whether the traffic sign is a scene placed on the vehicle is judged, and if the traffic sign is placed on the vehicle, the temporary traffic sign is determined.
It should be noted that, the implementation manner of analyzing the position relationship between the signboard region and the target region to determine whether the traffic signboard is the temporary traffic signboard is only an example, and the position relationship between the corresponding strategy analysis regions may be set and selected as needed to determine the temporary traffic signboard, and multiple determination manners may also be used in combination, which is not limited herein.
According to the temporary traffic sign board identification method, the target road image containing the traffic sign board is obtained, and the sign board area in the road image is detected. And further extracting the mark information in the signboard area, matching the mark information with preset target information, and if the matching fails, performing pixel semantic segmentation processing on the road image to acquire one or more reference areas. Further, a target area and a corresponding target area type are determined from one or more reference areas, a target strategy corresponding to the target area type is obtained, and the position relation between the signboard area and the target area is analyzed according to the target strategy to determine whether the traffic signboard is a temporary traffic signboard. Therefore, the temporary traffic sign can be identified based on the position relation between the sign and the target area, and the identification efficiency and accuracy are improved.
Based on the above embodiments, the temporary traffic sign may also be determined comprehensively through multiple frame sequential images in the embodiments of the present application, which is described as follows.
Fig. 2 is a schematic flow chart of another temporary traffic sign identification method according to an embodiment of the present disclosure, and as shown in fig. 2, the method includes:
In this embodiment, a road image sequence including the traffic signboard is photographed by the image capturing device, where the road image sequence may include a plurality of road images. The shooting position is, for example, a position where the image acquisition device shoots the road image, and each frame of the road image corresponds to one shooting position.
As an example, the distance between the shooting position of each road image and the traffic sign is acquired, and the road image whose distance satisfies the condition is taken as the target road image. Wherein the condition is that the distance is within a preset range, for example.
As another example, the area size of the traffic signboard on the image may be obtained, and if the ratio of the area of the traffic signboard on the image to the whole image is greater than the preset ratio, the road image is determined to be the target road image.
Therefore, for the multi-frame road image actually acquired, the road image may be unclear due to the distance or shooting, and the recognition result may be affected. Therefore, the target road image is determined from the road image sequence according to the distance change of the photographing position and the area size change of the traffic signboard on the image to recognize the temporary traffic signboard according to the target road image, thereby improving the recognition accuracy.
In one embodiment of the present application, a road image sequence including a traffic signboard, for example, including a plurality of frames of road images, may also be captured. And respectively identifying the multiple frames of images to obtain whether the multiple traffic signboards are the identification results of the temporary traffic signboards, and if the number of the first identification results of the temporary traffic signboards is larger than the number of the second identification results of the temporary traffic signboards, determining that the temporary traffic signboards are the temporary traffic signboards. Therefore, the temporary traffic sign is identified according to the principle of majority judgment, and the identification accuracy is improved.
Fig. 3 is a schematic flow chart of another temporary traffic sign identification method according to an embodiment of the present application, and as shown in fig. 3, the method includes:
In this embodiment, the road image is marked with a shooting position.
There may be one or more reference regions. For example, as shown in fig. 4, a signpost area and each reference area in a road image are obtained by pixel semantic segmentation processing, where in fig. 4, a is the road image, b is a semantic segmentation map, and in the semantic segmentation map, an area 1 is the signpost area, an area 2 is the fence area, and an area 3 is the road surface area.
As an example, taking a road surface area as an example, the position relationship between the signboard region and the road surface area is analyzed, and the region association feature extracted according to the position relationship may include whether the traffic signboard is placed on the ground.
In this embodiment, the distance between the shooting position of the road image and the traffic sign is calculated, and the distance is used as the shooting distance feature of the road image.
And step 304, inputting the shooting distance characteristic and the area association characteristic into a pre-trained judgment model for processing, and outputting whether the traffic sign is a temporary sign.
In one embodiment of the present application, a sample image including a traffic sign is collected in advance, and whether it is a temporary sign is marked in the sample image. Optionally, temporary sign categories may also be labeled, which may include speed limits, for example. And extracting the associated features and the shooting distance features according to the multi-frame sample images, inputting the associated features and the shooting distance features into a preset model for processing, obtaining a prediction result, and adjusting the model parameters until the prediction result is consistent with the labeling result, thereby realizing the training judgment model.
As an example, the road image includes 10 frames, the association features and the shooting distance features of the 10 frames of road image are obtained, the association features include whether the traffic sign is on the ground or not, the association features and the shooting distance features corresponding to the 10 frames of road image are combined into a multi-dimensional vector, the multi-dimensional vector is input into the determination model for processing, and the identification result of whether the traffic sign is a temporary traffic sign or not is output.
According to the temporary traffic sign identification method, the temporary traffic sign is comprehensively judged through the multi-frame sequence images, and the identification accuracy is further improved.
In order to realize the embodiment, the application also provides a temporary traffic sign plate recognition device.
Fig. 5 is a schematic structural diagram of a temporary traffic sign recognition apparatus according to an embodiment of the present application, and as shown in fig. 5, the apparatus includes: the system comprises an acquisition module 10, a processing module 20, a determination module 30 and an identification module 40.
The acquiring module 10 is configured to acquire a target road image including a traffic sign and detect a sign area in the target road image.
And the processing module 20 is configured to extract the sign information in the sign board region, match the sign information with preset target information, and perform pixel semantic segmentation processing on the target road image if matching fails, so as to obtain one or more reference regions.
A determining module 30, configured to determine a target area and a corresponding target area type from the one or more reference areas, and obtain a target policy corresponding to the target area type.
And the identification module 40 is configured to perform position relationship analysis on the signboard region and the target region according to the target policy, and determine whether the traffic signboard is a temporary traffic signboard.
On the basis of fig. 5, the apparatus shown in fig. 6 further includes: a match determination module 50.
The matching determination module 50 is configured to determine that the traffic sign is a temporary traffic sign if the matching is successful.
In an embodiment of the present application, the obtaining module 10 is specifically configured to: shooting a road image sequence which comprises a traffic signboard and is marked with a shooting position; and determining the target road image from the road image sequence according to the distance change of the shooting position and the area size change of the traffic signboard on the image.
In an embodiment of the present application, the target area type is a road surface, and the identification module 40 is specifically configured to: judging whether the signboard region and the road surface region have an overlapping region, if so, determining that the traffic signboard is a temporary traffic signboard, and if not, judging whether the distance between the signboard region and the road surface region is smaller than a preset threshold value; and if the distance is smaller than the preset threshold value, determining that the traffic sign board is a temporary traffic sign board.
In an embodiment of the present application, the type of the target area is a fence, and the identification module 40 is specifically configured to: judging whether the distance between the signboard area and the fence area is smaller than a preset threshold value or not; if the distance is smaller than the preset threshold value, determining that the traffic sign board is a temporary traffic sign board; if the distance is not smaller than the preset threshold value, judging whether the height of the signboard area is lower than that of the fence area; if yes, determining that the traffic sign board is a temporary traffic sign board.
In an embodiment of the present application, the target area type is a vehicle, and the identification module 40 is specifically configured to: judging whether the signboard area and the vehicle area have an overlapping area; and if the overlapped area is determined to exist, determining that the traffic sign board is a temporary traffic sign board.
The explanation of the temporary traffic sign recognition method in the foregoing embodiment is also applicable to the temporary traffic sign recognition apparatus in this embodiment, and will not be described again here.
The temporary traffic sign recognition device of the embodiment of the application detects a sign area in a road image by acquiring a target road image containing a traffic sign. And further extracting the mark information in the signboard area, matching the mark information with preset target information, and if the matching fails, performing pixel semantic segmentation processing on the road image to acquire one or more reference areas. Further, a target area and a corresponding target area type are determined from one or more reference areas, a target strategy corresponding to the target area type is obtained, and the position relation between the signboard area and the target area is analyzed according to the target strategy to determine whether the traffic signboard is a temporary traffic signboard. Therefore, the temporary traffic sign can be identified based on the position relation between the sign and the target area, and the identification efficiency and accuracy are improved.
In order to implement the above embodiments, the present application also proposes a computer program product, wherein instructions of the computer program product, when executed by a processor, implement the temporary traffic sign recognition method according to any of the foregoing embodiments.
According to an embodiment of the present application, an electronic device and a readable storage medium are also provided.
Fig. 7 is a block diagram of an electronic device according to an embodiment of the present application. Electronic devices are intended to represent various forms of digital computers, such as laptops, desktops, workstations, personal digital assistants, servers, blade servers, mainframes, and other appropriate computers. The electronic device may also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions, are meant to be examples only, and are not meant to limit implementations of the present application that are described and/or claimed herein.
As shown in fig. 7, the electronic apparatus includes: one or more processors 701, a memory 702, and interfaces for connecting the various components, including a high-speed interface and a low-speed interface. The various components are interconnected using different buses and may be mounted on a common motherboard or in other manners as desired. The processor may process instructions for execution within the electronic device, including instructions stored in or on the memory to display graphical information of a GUI on an external input/output apparatus (such as a display device coupled to the interface). In other embodiments, multiple processors and/or multiple buses may be used, along with multiple memories and multiple memories, as desired. Also, multiple electronic devices may be connected, with each device providing portions of the necessary operations (e.g., as a server array, a group of blade servers, or a multi-processor system). In fig. 7, one processor 701 is taken as an example.
The memory 702 is a non-transitory computer readable storage medium as provided herein. Wherein the memory stores instructions executable by the at least one processor to cause the at least one processor to perform the temporary traffic sign recognition methods provided herein. The non-transitory computer-readable storage medium of the present application stores computer instructions for causing a computer to perform the temporary traffic sign recognition method provided by the present application.
The memory 702, which is a non-transitory computer-readable storage medium, may be used to store non-transitory software programs, non-transitory computer-executable programs, and modules, such as program instructions/modules corresponding to the temporary traffic sign recognition method in the embodiment of the present application (for example, the acquisition module 10, the processing module 20, the determination module 30, and the recognition module 40 shown in fig. 5). The processor 701 executes various functional applications of the server and data processing by running non-transitory software programs, instructions, and modules stored in the memory 702, that is, implements the temporary traffic sign recognition method in the above-described method embodiment.
The memory 702 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 according to use of the electronic device, and the like. Further, the memory 702 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 702 may optionally include memory located remotely from the processor 701, which may be connected to the electronic device via a network. Examples of such networks include, but are not limited to, the internet, intranets, local area networks, mobile communication networks, and combinations thereof.
The electronic device of the temporary traffic sign recognition method may further include: an input device 703 and an output device 704. The processor 701, the memory 702, the input device 703 and the output device 704 may be connected by a bus or other means, and fig. 7 illustrates an example of a connection by a bus.
The input device 703 may receive input numeric or character information and generate key signal inputs related to user settings and function control of the electronic apparatus, such as a touch screen, a keypad, a mouse, a track pad, a touch pad, a pointing stick, one or more mouse buttons, a track ball, a joystick, or other input devices. The output devices 704 may include a display device, auxiliary lighting devices (e.g., LEDs), and tactile feedback devices (e.g., vibrating motors), among others. The display device may include, but is not limited to, a Liquid Crystal Display (LCD), a Light Emitting Diode (LED) display, and a plasma display. In some implementations, the display device can be a touch screen.
Various implementations of the systems and techniques described here can be realized in digital electronic circuitry, integrated circuitry, application specific ASICs (application specific integrated circuits), computer hardware, firmware, software, and/or combinations thereof. These various embodiments may include: implemented in one or more computer programs that are executable and/or interpretable on a programmable system including at least one programmable processor, which may be special or general purpose, receiving data and instructions from, and transmitting data and instructions to, a storage system, at least one input device, and at least one output device.
These computer programs (also known as programs, software applications, or code) include machine instructions for a programmable processor, and may be implemented using high-level procedural and/or object-oriented programming languages, and/or assembly/machine languages. As used herein, the terms "machine-readable medium" and "computer-readable medium" refer to any computer program product, apparatus, and/or device (e.g., magnetic discs, optical disks, memory, Programmable Logic Devices (PLDs)) used to provide machine instructions and/or data to a programmable processor, including a machine-readable medium that receives machine instructions as a machine-readable signal. The term "machine-readable signal" refers to any signal used to provide machine instructions and/or data to a programmable processor.
To provide for interaction with a user, the systems and techniques described here can be implemented on a computer having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to a user; and a keyboard and a pointing device (e.g., a mouse or a trackball) by which a user can provide input to the computer. Other kinds of devices may also be used to provide for interaction with a user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form, including acoustic, speech, or tactile input.
The systems and techniques described here can be implemented in a computing system that includes a back-end component (e.g., as a data server), or that includes a middleware component (e.g., an application server), or that includes a front-end component (e.g., a user computer having a graphical user interface or a web browser through which a user can interact with an implementation of the systems and techniques described here), or any combination of such back-end, middleware, or front-end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: local Area Networks (LANs), Wide Area Networks (WANs), and the Internet.
The computer system may include clients and servers. A client and server are generally remote from each other and typically interact through a communication network. The relationship of client and server arises by virtue of computer programs running on the respective computers and having a client-server relationship to each other.
It should be understood that various forms of the flows shown above may be used, with steps reordered, added, or deleted. For example, the steps described in the present application may be executed in parallel, sequentially, or in different orders, and the present invention is not limited thereto as long as the desired results of the technical solutions disclosed in the present application can be achieved.
The above-described embodiments should not be construed as limiting the scope of the present application. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions may be made in accordance with design requirements and other factors. Any modification, equivalent replacement, and improvement made within the spirit and principle of the present application shall be included in the protection scope of the present application.
Claims (14)
1. A temporary traffic sign identification method, comprising:
acquiring a target road image containing a traffic sign, and detecting a sign area in the target road image;
extracting the sign information in the sign board area, matching the sign information with preset target information, and if the matching fails, performing pixel semantic segmentation processing on the target road image to obtain one or more reference areas;
determining a target area and a corresponding target area type from the one or more reference areas, and acquiring a target strategy corresponding to the target area type;
and analyzing the position relation between the signboard area and the target area according to the target strategy to determine whether the traffic signboard is a temporary traffic signboard.
2. The method of claim 1, wherein said obtaining an image of a target roadway including a traffic sign comprises:
shooting a road image sequence which comprises a traffic signboard and is marked with a shooting position;
and determining the target road image from the road image sequence according to the distance change of the shooting position and the area size change of the traffic signboard on the image.
3. The method of claim 1, wherein the target area type is a road surface, and the analyzing the position relationship between the signboard area and the target area according to the target strategy to determine whether the traffic signboard is a temporary traffic signboard comprises:
judging whether the signboard region and the road surface region have an overlapping region, if so, determining that the traffic signboard is a temporary traffic signboard, and if not, judging whether the distance between the signboard region and the road surface region is smaller than a preset threshold value;
and if the distance is smaller than the preset threshold value, determining that the traffic sign board is a temporary traffic sign board.
4. The method of claim 1, wherein the target area type is a fence, and the analyzing the location relationship between the signboard region and the target area according to the target policy to determine whether the traffic signboard is a temporary traffic signboard comprises:
judging whether the distance between the signboard area and the fence area is smaller than a preset threshold value or not;
if the distance is smaller than the preset threshold value, determining that the traffic sign board is a temporary traffic sign board;
if the distance is not smaller than the preset threshold value, judging whether the height of the signboard area is lower than that of the fence area;
if yes, determining that the traffic sign board is a temporary traffic sign board.
5. The method of claim 1, wherein the target area type is a vehicle, the analyzing the location relationship between the signboard region and the target area according to the target policy to determine whether the traffic signboard is a temporary traffic signboard comprises:
judging whether the signboard area and the vehicle area have an overlapping area;
and if the overlapped area is determined to exist, determining that the traffic sign board is a temporary traffic sign board.
6. The method of claim 1, wherein after matching the flag information with preset target information, further comprising:
and if the matching is successful, determining that the traffic sign board is a temporary traffic sign board.
7. A temporary traffic sign recognition device, comprising:
the system comprises an acquisition module, a display module and a display module, wherein the acquisition module is used for acquiring a target road image containing a traffic sign and detecting a sign area in the target road image;
the processing module is used for extracting the sign information in the sign board area, matching the sign information with preset target information, and if the matching fails, performing pixel semantic segmentation processing on the target road image to acquire one or more reference areas;
the determining module is used for determining a target area and a corresponding target area type from the one or more reference areas and acquiring a target strategy corresponding to the target area type;
and the identification module is used for analyzing the position relation between the signboard area and the target area according to the target strategy and determining whether the traffic signboard is a temporary traffic signboard.
8. The apparatus of claim 7, wherein the acquisition module is specifically configured to:
shooting a road image sequence which comprises a traffic signboard and is marked with a shooting position;
and determining the target road image from the road image sequence according to the distance change of the shooting position and the area size change of the traffic signboard on the image.
9. The apparatus of claim 7, wherein the target area type is a road surface, the identification module being specifically configured to:
judging whether the signboard region and the road surface region have an overlapping region, if so, determining that the traffic signboard is a temporary traffic signboard, and if not, judging whether the distance between the signboard region and the road surface region is smaller than a preset threshold value;
and if the distance is smaller than the preset threshold value, determining that the traffic sign board is a temporary traffic sign board.
10. The apparatus of claim 7, wherein the target area type is fence, the identification module being specifically configured to:
judging whether the distance between the signboard area and the fence area is smaller than a preset threshold value or not;
if the distance is smaller than the preset threshold value, determining that the traffic sign board is a temporary traffic sign board;
if the distance is not smaller than the preset threshold value, judging whether the height of the signboard area is lower than that of the fence area;
if yes, determining that the traffic sign board is a temporary traffic sign board.
11. The apparatus of claim 7, wherein the target area type is a vehicle, the identification module being specifically configured to:
judging whether the signboard area and the vehicle area have an overlapping area;
and if the overlapped area is determined to exist, determining that the traffic sign board is a temporary traffic sign board.
12. The apparatus of claim 7, further comprising:
and the matching determination module is used for determining that the traffic sign board is a temporary traffic sign board if the matching is successful.
13. An electronic device, comprising:
at least one processor; and
a memory communicatively coupled to the at least one processor; wherein the content of the first and second substances,
the memory stores instructions executable by the at least one processor to enable the at least one processor to perform the temporary traffic sign identification method of any of claims 1-6.
14. A non-transitory computer readable storage medium storing computer instructions for causing a computer to perform the temporary traffic sign recognition method of any one of claims 1-6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010148754.7A CN113361303B (en) | 2020-03-05 | 2020-03-05 | Temporary traffic sign board identification method, device and equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010148754.7A CN113361303B (en) | 2020-03-05 | 2020-03-05 | Temporary traffic sign board identification method, device and equipment |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113361303A true CN113361303A (en) | 2021-09-07 |
| CN113361303B CN113361303B (en) | 2023-06-23 |
Family
ID=77523747
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010148754.7A Active CN113361303B (en) | 2020-03-05 | 2020-03-05 | Temporary traffic sign board identification method, device and equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113361303B (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2023077940A1 (en) * | 2021-11-03 | 2023-05-11 | 北京沃东天骏信息技术有限公司 | Recognition method and apparatus, processing method and apparatus, and intelligent detection system |
| CN117523535A (en) * | 2024-01-08 | 2024-02-06 | 浙江零跑科技股份有限公司 | Traffic sign recognition method, terminal equipment and storage medium |
Citations (17)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US6185314B1 (en) * | 1997-06-19 | 2001-02-06 | Ncr Corporation | System and method for matching image information to object model information |
| KR20150116673A (en) * | 2014-04-08 | 2015-10-16 | 한양대학교 산학협력단 | Database construction method for recognizing traffic signs and image recognition device for vehicle using the same |
| CN106127153A (en) * | 2016-06-24 | 2016-11-16 | 南京林业大学 | The traffic sign recognition methods of Vehicle-borne Laser Scanning cloud data |
| CN106557759A (en) * | 2016-11-25 | 2017-04-05 | 北京小米移动软件有限公司 | A kind of sign board information getting method and device |
| US20170236284A1 (en) * | 2016-02-13 | 2017-08-17 | University Of Rochester | Registration of aerial imagery to vector road maps with on-road vehicular detection and tracking |
| CN107679508A (en) * | 2017-10-17 | 2018-02-09 | 广州汽车集团股份有限公司 | Road traffic sign detection recognition methods, apparatus and system |
| US20180300549A1 (en) * | 2017-04-12 | 2018-10-18 | Baidu Online Network Technology (Beijing) Co., Ltd. | Road detecting method and apparatus |
| CN109389167A (en) * | 2018-09-29 | 2019-02-26 | 武汉中海庭数据技术有限公司 | Traffic sign recognition method and system |
| CN109409247A (en) * | 2018-09-30 | 2019-03-01 | 百度在线网络技术（北京）有限公司 | Traffic sign recognition method and device |
| KR20190076195A (en) * | 2017-12-22 | 2019-07-02 | 남서울대학교 산학협력단 | Apparatus and method for recognizing road traffic sign information |
| CN110163153A (en) * | 2019-05-23 | 2019-08-23 | 百度在线网络技术（北京）有限公司 | The method and device on traffic mark board boundary for identification |
| CN110334601A (en) * | 2019-06-04 | 2019-10-15 | 武汉极目智能技术有限公司 | A kind of speed(-)limit sign board recognition methods of combination machine learning and computer vision |
| US20190325235A1 (en) * | 2018-04-19 | 2019-10-24 | Here Global B.V. | Method, apparatus, and system for traffic sign learning |
| US20190325349A1 (en) * | 2018-04-19 | 2019-10-24 | Here Global B.V. | Method, apparatus, and system for traffic sign learning based on road network connectivity |
| CN110378957A (en) * | 2019-06-05 | 2019-10-25 | 上海交通大学 | Torpedo tank car visual identity and localization method and its system towards metallurgical operation |
| EP3584742A1 (en) * | 2018-06-19 | 2019-12-25 | KPIT Technologies Ltd. | System and method for traffic sign recognition |
| CN110659550A (en) * | 2018-06-29 | 2020-01-07 | 比亚迪股份有限公司 | Traffic sign recognition method, traffic sign recognition device, computer equipment and storage medium |
-
2020
- 2020-03-05 CN CN202010148754.7A patent/CN113361303B/en active Active
Patent Citations (17)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US6185314B1 (en) * | 1997-06-19 | 2001-02-06 | Ncr Corporation | System and method for matching image information to object model information |
| KR20150116673A (en) * | 2014-04-08 | 2015-10-16 | 한양대학교 산학협력단 | Database construction method for recognizing traffic signs and image recognition device for vehicle using the same |
| US20170236284A1 (en) * | 2016-02-13 | 2017-08-17 | University Of Rochester | Registration of aerial imagery to vector road maps with on-road vehicular detection and tracking |
| CN106127153A (en) * | 2016-06-24 | 2016-11-16 | 南京林业大学 | The traffic sign recognition methods of Vehicle-borne Laser Scanning cloud data |
| CN106557759A (en) * | 2016-11-25 | 2017-04-05 | 北京小米移动软件有限公司 | A kind of sign board information getting method and device |
| US20180300549A1 (en) * | 2017-04-12 | 2018-10-18 | Baidu Online Network Technology (Beijing) Co., Ltd. | Road detecting method and apparatus |
| CN107679508A (en) * | 2017-10-17 | 2018-02-09 | 广州汽车集团股份有限公司 | Road traffic sign detection recognition methods, apparatus and system |
| KR20190076195A (en) * | 2017-12-22 | 2019-07-02 | 남서울대학교 산학협력단 | Apparatus and method for recognizing road traffic sign information |
| US20190325235A1 (en) * | 2018-04-19 | 2019-10-24 | Here Global B.V. | Method, apparatus, and system for traffic sign learning |
| US20190325349A1 (en) * | 2018-04-19 | 2019-10-24 | Here Global B.V. | Method, apparatus, and system for traffic sign learning based on road network connectivity |
| EP3584742A1 (en) * | 2018-06-19 | 2019-12-25 | KPIT Technologies Ltd. | System and method for traffic sign recognition |
| CN110659550A (en) * | 2018-06-29 | 2020-01-07 | 比亚迪股份有限公司 | Traffic sign recognition method, traffic sign recognition device, computer equipment and storage medium |
| CN109389167A (en) * | 2018-09-29 | 2019-02-26 | 武汉中海庭数据技术有限公司 | Traffic sign recognition method and system |
| CN109409247A (en) * | 2018-09-30 | 2019-03-01 | 百度在线网络技术（北京）有限公司 | Traffic sign recognition method and device |
| CN110163153A (en) * | 2019-05-23 | 2019-08-23 | 百度在线网络技术（北京）有限公司 | The method and device on traffic mark board boundary for identification |
| CN110334601A (en) * | 2019-06-04 | 2019-10-15 | 武汉极目智能技术有限公司 | A kind of speed(-)limit sign board recognition methods of combination machine learning and computer vision |
| CN110378957A (en) * | 2019-06-05 | 2019-10-25 | 上海交通大学 | Torpedo tank car visual identity and localization method and its system towards metallurgical operation |
Non-Patent Citations (1)
| Title |
|---|
| 杜影丽;贾永红;韩静敏;: "自然场景车载视频道路交通限速标志的检测与识别方法", 测绘地理信息, no. 02, pages 32 - 34 * |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2023077940A1 (en) * | 2021-11-03 | 2023-05-11 | 北京沃东天骏信息技术有限公司 | Recognition method and apparatus, processing method and apparatus, and intelligent detection system |
| CN117523535A (en) * | 2024-01-08 | 2024-02-06 | 浙江零跑科技股份有限公司 | Traffic sign recognition method, terminal equipment and storage medium |
| CN117523535B (en) * | 2024-01-08 | 2024-04-12 | 浙江零跑科技股份有限公司 | Traffic sign recognition method, terminal equipment and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113361303B (en) | 2023-06-23 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111709328B (en) | Vehicle tracking method and device and electronic equipment | |
| CN112149636B (en) | Method, device, electronic equipment and storage medium for detecting target object | |
| CN111275983B (en) | Vehicle tracking method, device, electronic equipment and computer-readable storage medium | |
| CN111460967B (en) | Illegal building identification method, device, equipment and storage medium | |
| CN111833340A (en) | Image detection method, image detection device, electronic equipment and storage medium | |
| CN110968718B (en) | Target detection model negative sample mining method and device and electronic equipment | |
| CN111292531B (en) | Tracking method, device and equipment of traffic signal lamp and storage medium | |
| CN111612820A (en) | Multi-target tracking method, and training method and device of feature extraction model | |
| CN110723432A (en) | Garbage classification method and augmented reality equipment | |
| CN112507949A (en) | Target tracking method and device, road side equipment and cloud control platform | |
| US20210110168A1 (en) | Object tracking method and apparatus | |
| CN111832568A (en) | License plate recognition method, and training method and device of license plate recognition model | |
| CN111723768A (en) | Method, device, equipment and storage medium for vehicle weight recognition | |
| CN110717933B (en) | Post-processing method, device, equipment and medium for moving object missed detection | |
| CN111275011B (en) | Mobile traffic light detection method and device, electronic equipment and storage medium | |
| CN113091757B (en) | Map generation method and device | |
| CN111767831B (en) | Method, apparatus, device and storage medium for processing image | |
| CN112883902A (en) | Video detection method and device, electronic equipment and storage medium | |
| CN111832658B (en) | Point-of-interest information processing method and device, electronic equipment and storage medium | |
| CN113673281B (en) | Speed limit information determining method, device, equipment and storage medium | |
| CN111783639A (en) | Image detection method and device, electronic equipment and readable storage medium | |
| CN113361303B (en) | Temporary traffic sign board identification method, device and equipment | |
| CN111950345A (en) | Camera identification method and device, electronic equipment and storage medium | |
| CN111783619A (en) | Human body attribute identification method, device, equipment and storage medium | |
| CN111783613B (en) | Anomaly detection method, model training method, device, equipment and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |