CN113487688A - Road sign detection method and device and computer readable storage medium - Google Patents
Road sign detection method and device and computer readable storage medium Download PDFInfo
- Publication number
- CN113487688A CN113487688A CN202110542215.6A CN202110542215A CN113487688A CN 113487688 A CN113487688 A CN 113487688A CN 202110542215 A CN202110542215 A CN 202110542215A CN 113487688 A CN113487688 A CN 113487688A
- Authority
- CN
- China
- Prior art keywords
- pixel
- road sign
- detection
- initial
- image group
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000001514 detection method Methods 0.000 title claims abstract description 147
- 230000011218 segmentation Effects 0.000 claims abstract description 88
- 238000012544 monitoring process Methods 0.000 claims abstract description 38
- 238000009825 accumulation Methods 0.000 claims description 3
- 238000000034 method Methods 0.000 abstract description 8
- 238000010586 diagram Methods 0.000 description 10
- 238000011156 evaluation Methods 0.000 description 6
- 239000000284 extract Substances 0.000 description 6
- 230000008878 coupling Effects 0.000 description 3
- 238000010168 coupling process Methods 0.000 description 3
- 238000005859 coupling reaction Methods 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 3
- 238000012986 modification Methods 0.000 description 3
- 230000004048 modification Effects 0.000 description 3
- 238000012545 processing Methods 0.000 description 3
- 238000004891 communication Methods 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 230000018109 developmental process Effects 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 108010001267 Protein Subunits Proteins 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000004590 computer program Methods 0.000 description 1
- 238000006073 displacement reaction Methods 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 230000006386 memory function Effects 0.000 description 1
- 238000012216 screening Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/90—Determination of colour characteristics
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/11—Region-based segmentation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10016—Video; Image sequence
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30232—Surveillance
Landscapes
- Engineering & Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Traffic Control Systems (AREA)
- Image Analysis (AREA)
Abstract
The application discloses a road sign detection method, a device and a computer readable storage medium, wherein the road sign detection method comprises the following steps: acquiring a monitoring video and extracting an initial image group in the monitoring video, wherein the initial image group comprises a preset number of images; inputting the initial image group into a preset detection segmentation model so as to set the pixel value of a mark position pixel point of an image in the initial image group as a first pixel value and set the pixel value of a non-mark position pixel point as a second pixel value; accumulating pixel values of pixel points of images in the initial image group, defining the pixel points with the accumulated pixel values larger than the preset pixel values as pixel points with road signs, and generating an initial road sign segmentation graph based on all the pixel points with the road signs. According to the method and the device, the detection and segmentation results of the multi-frame images are accumulated, and the road sign area is confirmed according to the pixel accumulated value, so that the accuracy of the road marking segmentation result can be effectively improved.
Description
Technical Field
The present application relates to the field of intelligent traffic technologies, and in particular, to a road sign detection method, apparatus, and computer-readable storage medium.
Background
Along with the continuous development of society and the continuous progress of science and technology, the current requirements cannot be met by using an artificial semi-intelligent method for urban road traffic management, as the traffic flow is continuously increased, more scenes are obtained, the scene is wider, and the problem that a traffic police cannot find out the dirty and damaged road signs in time in a few two-line cities is caused, so that the traffic direction of a crossroad is wrong, the traffic jam is caused, and the operation and maintenance work of urban traffic is seriously influenced, so that the development of an intelligent detection method for the damage of the traffic road signs is imperative.
At present, the identification technology for the road signs only uses single-frame information, so that the problem of shielding cannot be solved, and whether the road signs detected before and after are the same road sign target or not cannot be accurately judged along with the time lapse, camera shake and other factors.
Disclosure of Invention
The application provides a road sign detection method, a road sign detection device and a computer readable storage medium.
In order to solve the above technical problem, a first technical solution provided by the present application is: provided is a road sign detection method, including: acquiring a monitoring video and extracting an initial image group in the monitoring video, wherein the initial image group comprises a preset number of images; inputting the initial image group into a preset detection segmentation model so as to set the pixel value of a mark position pixel point of an image in the initial image group as a first pixel value and set the pixel value of a non-mark position pixel point as a second pixel value; accumulating pixel values of pixel points of images in the initial image group, defining the pixel points with the accumulated pixel values larger than the preset pixel values as pixel points with road signs, and generating an initial road sign segmentation graph based on all the pixel points with the road signs.
In order to solve the above technical problem, a second technical solution provided by the present application is: the road sign detection device comprises a processor and a memory connected with the processor, wherein the memory stores program instructions; the processor is configured to execute the memory-stored program instructions to implement: acquiring a monitoring video and extracting an initial image group in the monitoring video, wherein the initial image group comprises a preset number of images; inputting the initial image group into a preset detection segmentation model so as to set the pixel value of a mark position pixel point of an image in the initial image group as a first pixel value and set the pixel value of a non-mark position pixel point as a second pixel value; accumulating pixel values of pixel points of images in the initial image group, defining the pixel points with the accumulated pixel values larger than the preset pixel values as pixel points with road signs, and generating an initial road sign segmentation graph based on all the pixel points with the road signs.
In order to solve the above technical problem, a third technical solution provided by the present application is: providing a road sign detection device comprising a processor, a memory coupled to the processor, wherein the memory stores program instructions; the processor is to execute the memory-stored program instructions to implement: acquiring a monitoring video and extracting an initial image group in the monitoring video, wherein the initial image group comprises a preset number of images; inputting the initial image group into a preset detection segmentation model so as to set the pixel value of a mark position pixel point of an image in the initial image group as a first pixel value and set the pixel value of a non-mark position pixel point as a second pixel value; and accumulating pixel values of pixel points of the images in the initial image group, defining the pixel points with the accumulated pixel values larger than the preset pixel values as the pixel points with the road signs, and generating an initial road sign segmentation graph based on all the pixel points with the road signs.
In order to solve the above technical problem, a fourth technical solution provided by the present application is: there is provided a computer readable storage medium storing program instructions that when executed implement: acquiring a monitoring video and extracting an initial image group in the monitoring video, wherein the initial image group comprises a preset number of images; inputting the initial image group into a preset detection segmentation model so as to set the pixel value of a mark position pixel point of an image in the initial image group as a first pixel value and set the pixel value of a non-mark position pixel point as a second pixel value; and accumulating pixel values of pixel points of the images in the initial image group, defining the pixel points with the accumulated pixel values larger than the preset pixel values as the pixel points with the road signs, and generating an initial road sign segmentation graph based on all the pixel points with the road signs.
According to the road sign detection method, a monitoring video is obtained, and an initial image group in the monitoring video is extracted, wherein the initial image group comprises a preset number of images; inputting the initial image group into a preset detection segmentation model so as to set the pixel value of a mark position pixel point of an image in the initial image group as a first pixel value and set the pixel value of a non-mark position pixel point as a second pixel value; accumulating pixel values of pixel points of images in an initial image group, defining the pixel points with the accumulated pixel values larger than a preset pixel value as pixel points with road signs, and determining a road sign area according to the pixel accumulated value by accumulating detection segmentation results of multi-frame images so as to effectively improve the accuracy of road sign segmentation results; and generating an initial road sign segmentation graph based on all the pixel points with the road signs.
Drawings
In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings needed to be used in the description of the embodiments will be briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without creative efforts. Wherein:
FIG. 1 is a schematic flow chart diagram illustrating an embodiment of a road sign detection method provided herein;
FIG. 2 is a schematic representation of a road sign detection segmentation provided herein;
FIG. 3 is a schematic flow chart diagram illustrating another embodiment of a road sign detection method provided herein;
FIG. 4 is a schematic illustration of the updated standard road sign results provided herein;
FIG. 5 is a schematic flow chart diagram illustrating a method for detecting road signs in accordance with yet another embodiment of the present application;
FIG. 6 is a schematic structural diagram of an embodiment of a road sign detection apparatus provided herein;
FIG. 7 is a schematic structural diagram of another embodiment of a road sign detection device provided herein;
fig. 8 is a schematic structural diagram of a computer-readable storage medium provided in the present application.
Detailed Description
The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are only a part of the embodiments of the present application, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present application.
The present application will be described in detail with reference to the accompanying drawings and examples.
Referring to fig. 1, fig. 1 is a schematic flow chart of an embodiment of a road sign detection method provided in the present application.
The road sign detection method is applied to a road sign detection device, wherein the road sign detection device can be a server, a terminal device and a system formed by the cooperation of the server and the terminal device. Accordingly, each part, such as each unit, sub-unit, module, and sub-module, included in the road sign detection apparatus may be all disposed in the server, may be all disposed in the terminal device, and may be disposed in the server and the terminal device, respectively.
Further, the server may be hardware or software. When the server is hardware, it may be implemented as a distributed server cluster formed by multiple servers, or may be implemented as a single server. When the server is software, it may be implemented as a plurality of software or software modules, for example, software or software modules for providing distributed servers, or as a single software or software module, and is not limited herein.
It should be noted that, in the following description of the embodiments, the detection device is unified as the main execution body of the road sign detection method.
The road sign detection method of the embodiment of the disclosure specifically comprises the following steps:
step S11: the method comprises the steps of obtaining a monitoring video and extracting an initial image group in the monitoring video, wherein the initial image group comprises a preset number of images.
The detection device is connected with a monitoring camera arranged on a traffic road to acquire a monitoring video acquired by the monitoring camera. Then, the detection means extracts an initial image group composed of a preset number of frames of consecutive images from the surveillance video as initial detection data of the road sign detection method.
Specifically, taking a 25 frame rate surveillance video as an example, the detection apparatus acquires 20 seconds of surveillance video, i.e., extracts an initial image group from 500 frames of surveillance images. The detection device performs detection division every 5 frames of images to extract 100 frames of images to constitute an initial image group.
Step S12: and inputting the initial image group into a preset detection segmentation model so as to set the pixel value of the mark position pixel point of the image in the initial image group as a first pixel value and set the pixel value of the non-mark position pixel point as a second pixel value.
The detection device comprises a road sign detection, segmentation and tracking module, wherein the road sign detection, segmentation and tracking module trains a detection segmentation model for extracting road sign characteristics, namely the detection segmentation model is preset, such as a centerMask, a maskrnnn and other detection segmentation models.
The detection device sequentially inputs the initial image group into a preset detection segmentation model, the preset detection segmentation model identifies pixel points of road signs in the images and resets pixel values, specifically, the preset detection segmentation model sets the pixel values of the pixel points at the sign positions of the images in the initial image group as first pixel values, and sets the pixel values of the pixel points at the non-sign positions as second pixel values. The first pixel value is different from the second pixel value, and is used for distinguishing the mark position pixel points and the non-mark position pixel points from the pixel value.
For example, in the embodiment of the present application, the preset detection segmentation model may set the pixel value of the identified flag-position pixel point in the single frame image to 1, and set the pixel values of the remaining non-flag-position pixel points to 0.
Step S13: accumulating pixel values of pixel points of images in the initial image group, defining the pixel points with the accumulated pixel values larger than the preset pixel values as pixel points with road signs, and generating an initial road sign segmentation graph based on all the pixel points with the road signs.
The detection device can accumulate pixel values of pixel points of all images in the initial image group, and determine the road sign through the accumulated pixel values, so that the problem of being blocked can be well solved.
Specifically, the detection device defines the pixel points with the accumulated pixel values larger than the preset pixel values as the pixel points with the road signs, and then fills the connected domain formed by all the pixel points with the road signs to obtain the accurate road sign segmentation map. As shown in fig. 2, fig. 2 is a schematic diagram of road sign detection and segmentation provided by the present application. The first three pictures in fig. 2 are respectively three frames of images in the initial image group, which respectively show the situation that the road sign is blocked under different conditions, and the detection device obtains a fourth picture by accumulating at least three frames of images. As can be seen from the fourth picture, the road sign detection method according to the embodiment of the application can well solve the problem of being blocked, and generate an accurate road sign segmentation map. It is considered that the road sign division map generated here can be regarded as the road sign division result of the initialization criterion.
Further, in order to improve the accuracy of the road sign segmentation map, the embodiment of the present application sets that the value of the preset pixel value of the determination accumulation result should be greater than or equal to 30% of the number value of the initial image group. For example, when the preset number of the initial image group is 100 frames, the detection device may define the pixel points having the accumulated pixel values greater than 30 as the pixel points where the road sign exists.
In the embodiment of the application, a detection device acquires a monitoring video and extracts an initial image group in the monitoring video, wherein the initial image group comprises a preset number of images; inputting the initial image group into a preset detection segmentation model so as to set the pixel value of a mark position pixel point of an image in the initial image group as a first pixel value and set the pixel value of a non-mark position pixel point as a second pixel value; accumulating pixel values of pixel points of images in an initial image group, defining the pixel points with the accumulated pixel values larger than a preset pixel value as pixel points with road signs, and determining a road sign area according to the pixel accumulated value by accumulating detection segmentation results of multi-frame images so as to effectively improve the accuracy of road sign segmentation results; and generating an initial road sign segmentation graph based on all the pixel points with the road signs.
Furthermore, because camera settings such as a monitoring camera have a jitter problem, another road sign detection method is further provided in the embodiments of the present application, and the road sign is accurately corrected and corrected by detecting and segmenting subsequent images. Referring to fig. 3, fig. 3 is a schematic flow chart of another embodiment of a road sign detection method according to the present application.
The road sign detection method of the embodiment of the disclosure specifically comprises the following steps:
step S21: the method comprises the steps of obtaining a monitoring video and extracting an initial image group in the monitoring video, wherein the initial image group comprises a preset number of images.
Step S22: and inputting the initial image group into a preset detection segmentation model so as to set the pixel value of the mark position pixel point of the image in the initial image group as a first pixel value and set the pixel value of the non-mark position pixel point as a second pixel value.
Step S23: accumulating pixel values of pixel points of images in the initial image group, defining the pixel points with the accumulated pixel values larger than the preset pixel values as pixel points with road signs, and generating an initial road sign segmentation graph based on all the pixel points with the road signs.
The technical contents of step S21 to step S22 are described in detail in the above embodiments, and are not described herein again.
Step S24: and acquiring an updated image after the initial image group in the monitoring video.
Wherein, the detection device further extracts the updated image in the monitoring video, and the acquisition time sequence of the updated image is subsequent to the acquisition time sequence of the initial image group.
Step S25: and inputting the updated image into a preset detection segmentation model to obtain an updated road sign segmentation map of the updated image.
The detection device inputs the updated image into the preset detection segmentation model to obtain an updated road sign segmentation image of the updated image detection segmentation of the preset detection segmentation model.
Step S26: the area of the road sign is updated based on the overlapping area of the initial road sign segmentation map and the updated road sign segmentation map.
Among them, the camera shake phenomenon can be described as: the displacement is small for a short time and gradually shifts as time goes on. Therefore, as shown in fig. 4, the embodiment of the present application may continuously update the road sign segmentation result of the initialization criterion, such as the solid line surrounding area in fig. 4, by using the subsequent detection segmentation result of the updated image, such as the dashed line surrounding area in fig. 4.
Further, since the problem that the road sign is blocked may also occur in the updated image, the detection apparatus may further set a certain update condition, that is, the road sign segmentation result of the initialization criterion is updated only when the relationship between the updated road sign segmentation map of the update pattern and the initial road sign segmentation map satisfies the update condition.
Specifically, the update condition may be set such that the intersection ratio of the currently detected updated road sign segmentation map and the initial road sign segmentation map is greater than 0.8. First, the detection device calculates an intersection ratio of the calculated initial road sign segmentation map and the updated road sign segmentation map. Then, in the case where the intersection ratio of both is larger than 0.8, the area of the road sign is updated based on updating the initial road sign segmentation map to the updated road sign segmentation map.
In the embodiment of the application, the detection device tracks the road sign by dividing the road sign, solves the problem of road sign position inaccuracy after the camera picture deviates along with time deviation, and then ensures that the road sign area is completely sent into the evaluation module by comparing the images sent into the evaluation module by the IOU screening.
To further evaluate the degree of damage of the road sign in the current frame image, the detecting device may use the road sign segmentation map obtained in the above embodiment to calculate a sharpness evaluation value of the current frame image, and use the sharpness evaluation value of the current frame image to calculate a road sign damage degree indicator of the current frame image. Referring to fig. 5, fig. 5 is a schematic flowchart illustrating a road sign detection method according to another embodiment of the present application.
The road sign detection method of the embodiment of the disclosure specifically comprises the following steps:
step S31: and acquiring a detection image in the monitoring video, graying a road sign area corresponding to the initial road sign segmentation map in the detection image, and setting the pixel values of the rest non-road sign areas as third pixel values.
The detection device extracts a current frame detection image in the monitoring video, and maps the initial road sign segmentation image to the current frame detection image to obtain a road sign area in the current frame detection image.
First, the detection device calculates the sharpness of the detection image based on the pixel values of the detection image. The calculation formula is as follows:
D(x,y)＝|f(x+1,y)-f(x,y)|+|f(x,y+1)-f(x,y)|
wherein f (x, y) represents the pixel value of the pixel (x, y) of the detection image, D (x, y) represents the difference value of the pixel, and S represents the definition of the detection image.
The detection device then grays the road sign region corresponding to the initial road sign segmentation map in the detected image, and sets the pixel values of the remaining non-road sign regions to a third pixel value, which may be 0.
Step S32: the minimum definition of the detection image is calculated based on the pixel values of the road sign region and the non-road sign region of the detection image after graying.
The detection device inputs the grayed detection image into the mark damage degree evaluation module, and obtains the minimum definition Smin of the detection image based on the formula.
Step S33: and calculating the difference value of each pixel value in the detection image after graying, and setting the difference value not equal to 0 as a fourth pixel value, wherein the fourth pixel value is larger than the third pixel value.
Step S34: the maximum sharpness of the detection image is calculated based on the difference value of the detection image after the resetting.
The detection device needs to estimate the most serious damage condition of the road sign, specifically, the detection device resets the D (x, y) non-0 part to 255, and then calculates the maximum definition Smax of the detected image through the formula.
Step S35: and acquiring the road sign damage degree index of the detection image based on the minimum definition and the maximum definition of the detection image.
Finally, the detection device calculates the road sign damage degree index lambda of the current frame detection image as S/(Smax-Smin) based on the definition information. Wherein, 0 < lambda < 1, the larger the value of lambda, the more serious the road sign is damaged.
In addition, in combination with the above embodiment, the detection device may further send the road sign result satisfying the update condition in the road sign detection, division and tracking module to perform sign damage degree evaluation to obtain a current frame road sign damage degree index λ, and finally output the road sign damage degree index λ.
The embodiment of the application provides a quantitative standard for evaluating the damage degree of the road sign, so that workers can conveniently and timely learn the damage condition of the road sign on the traffic road.
The above embodiments are only one of the common cases of the present application and do not limit the technical scope of the present application, so that any minor modifications, equivalent changes or modifications made to the above contents according to the essence of the present application still fall within the technical scope of the present application.
With continuing reference to fig. 6, fig. 6 is a schematic structural diagram of an embodiment of a road sign detection device provided in the present application. The road sign detection device 50 includes a video acquisition module 51, a pixel division module 52, and a sign division module 53.
The video obtaining module 51 is configured to obtain a monitoring video and extract an initial image group in the monitoring video, where the initial image group includes a preset number of images.
The pixel segmentation module 52 is configured to input the initial image group into a preset detection segmentation model, so as to set a pixel value of a flag-position pixel point of an image in the initial image group to be a first pixel value, and set a pixel value of a non-flag-position pixel point to be a second pixel value.
The mark segmentation module 53 is configured to accumulate pixel values of pixels of the images in the initial image group, define pixels having pixel values larger than a preset pixel value after accumulation as pixels having a road mark, and generate an initial road mark segmentation map based on all pixels having a road mark.
Referring to fig. 7, fig. 7 is a schematic structural diagram of another embodiment of the road sign detecting device provided in the present application. The road sign detection means comprises a memory 62 and a processor 61 connected to each other.
The memory 62 is used to store program instructions for implementing the road sign detection method of any of the above.
The processor 61 is operative to execute program instructions stored in the memory 62.
The processor 61 may also be referred to as a CPU (Central Processing Unit). The processor 61 may be an integrated circuit chip having signal processing capabilities. The processor 61 may also be a 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, discrete gate or transistor logic, discrete hardware components. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like.
The storage 62 may be a memory bank, a TF card, etc., and may store all information in the string matching prediction apparatus, including the input raw data, the computer program, the intermediate operation results, and the final operation results. It stores and retrieves information based on the location specified by the controller. With the memory, the string matching prediction device has a memory function, and normal operation can be guaranteed. The memory of the string matching prediction device can be classified into a main memory (internal memory) and an auxiliary memory (external memory) according to the use, and also into an external memory and an internal memory. The external memory is usually a magnetic medium, an optical disk, or the like, and can store information for a long period of time. The memory refers to a storage component on the main board, which is used for storing data and programs currently being executed, but is only used for temporarily storing the programs and the data, and the data is lost when the power is turned off or the power is cut off.
In the several embodiments provided in the present application, it should be understood that the disclosed method and apparatus may be implemented in other ways. For example, the above-described apparatus embodiments are merely illustrative, and for example, a division of a module or a unit is merely a logical division, and an actual implementation may have another division, for example, a plurality of units or components may be combined or integrated into another system, or some features may be omitted, or not executed. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection through some interfaces, devices or units, and may be in an electrical, mechanical or other form.
Units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the embodiment.
In addition, functional units in the embodiments of the present application may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit. The integrated unit can be realized in a form of hardware, and can also be realized in a form of a software functional unit.
The integrated unit, if implemented in the form of a software functional unit and sold or used as a stand-alone product, may be stored in a computer readable storage medium. Based on such understanding, the technical solution of the present application may be substantially implemented or contributed to by the prior art, or all or part of the technical solution may be embodied in a software product, which is stored in a storage medium and includes instructions for causing a computer device (which may be a personal computer, a system server, a network device, or the like) or a processor (processor) to execute all or part of the steps of the method of the embodiments of the present application.
Please refer to fig. 8, which is a schematic structural diagram of a computer-readable storage medium according to the present application. The storage medium of the present application stores a program file 71 capable of implementing all the above-mentioned road sign detection methods, wherein the program file 71 may be stored in the storage medium in the form of a software product, and includes several instructions to enable a computer device (which may be a personal computer, a server, or a network device) or a processor (processor) to execute all or part of the steps of the methods according to the embodiments of the present application. The aforementioned storage device includes: various media capable of storing program codes, such as a usb disk, a mobile hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, or terminal devices, such as a computer, a server, a mobile phone, and a tablet.
The above embodiments are merely examples and are not intended to limit the scope of the present disclosure, and all modifications, equivalents, and flow charts using the contents of the specification and drawings of the present disclosure or those directly or indirectly applied to other related technical fields are intended to be included in the scope of the present disclosure.
Claims (10)
1. A road sign detection method, characterized by comprising:
acquiring a monitoring video and extracting an initial image group in the monitoring video, wherein the initial image group comprises a preset number of images;
inputting the initial image group into a preset detection segmentation model so as to set the pixel value of a mark position pixel point of an image in the initial image group as a first pixel value and set the pixel value of a non-mark position pixel point as a second pixel value;
and accumulating pixel values of pixel points of the images in the initial image group, defining the pixel points with the accumulated pixel values larger than the preset pixel values as the pixel points with the road signs, and generating an initial road sign segmentation graph based on all the pixel points with the road signs.
2. The road sign detection method according to claim 1,
the road sign detection method further comprises:
acquiring an updated image after the initial image group in the monitoring video;
inputting the updated image into the preset detection segmentation model to obtain an updated road sign segmentation map of the updated image;
updating the area of the road sign based on the overlapping area of the initial road sign segmentation map and the updated road sign segmentation map.
3. The road sign detection method according to claim 2,
the updating of the area of the road sign based on the overlapping area of the initial road sign segmentation map and the updated road sign segmentation map comprises:
calculating the intersection ratio of the initial road sign segmentation map and the updated road sign segmentation map;
and updating the initial road sign segmentation map based on the updated road sign segmentation map to update the area of the road sign when the intersection ratio is greater than a preset intersection ratio.
4. The road sign detection method according to claim 1,
the value of the preset pixel value is greater than or equal to 30% of the value of the preset number.
5. The road sign detection method according to claim 1,
the road sign detection method further comprises:
acquiring a detection image in the monitoring video, graying a road sign area corresponding to an initial road sign segmentation map in the detection image, and setting pixel values of the rest non-road sign areas as third pixel values;
calculating the minimum definition of the detection image based on the pixel values of the road sign region and the non-road sign region of the grayed detection image;
calculating a difference value of each pixel value in the detection image after graying, and setting the difference value not equal to 0 as a fourth pixel value, wherein the fourth pixel value is larger than the third pixel value;
calculating the maximum definition of the detection image based on the difference value of the detection image after reset;
and acquiring a road sign damage degree index of the detection image based on the minimum definition and the maximum definition of the detection image.
6. The road sign detection method according to claim 5,
the obtaining of the road sign damage degree index of the detection image based on the minimum definition and the maximum definition of the detection image comprises:
calculating a sharpness of the detection image based on pixel values of the detection image;
and acquiring the road sign damage degree index of the detection image based on the definition, the minimum definition and the maximum definition of the detection image.
7. The road sign detection method according to claim 6,
the calculating the sharpness of the detection image based on the pixel values of the detection image comprises:
acquiring a pixel value of each pixel point on the detection image;
calculating the difference value of each pixel point and the adjacent pixel points in sequence;
and accumulating the difference values of all pixel points in the detection image to obtain the definition of the detection image.
8. The road sign detection device is characterized by comprising a video acquisition module, a pixel segmentation module and a sign segmentation module;
the video acquisition module is used for acquiring a monitoring video and extracting an initial image group in the monitoring video, wherein the initial image group comprises a preset number of images;
the pixel segmentation module is used for inputting the initial image group into a preset detection segmentation model so as to set the pixel value of a mark position pixel point of an image in the initial image group as a first pixel value and set the pixel value of a non-mark position pixel point as a second pixel value;
the mark segmentation module is used for accumulating pixel point pixel values of the images in the initial image group, defining pixel points with pixel values larger than a preset pixel value after accumulation as pixel points with road marks, and generating an initial road mark segmentation image based on all the pixel points with the road marks.
9. A road sign detection device, comprising a processor, a memory connected to the processor, wherein,
the memory stores program instructions;
the processor is to execute the memory-stored program instructions to implement:
acquiring a monitoring video and extracting an initial image group in the monitoring video, wherein the initial image group comprises a preset number of images;
inputting the initial image group into a preset detection segmentation model so as to set the pixel value of a mark position pixel point of an image in the initial image group as a first pixel value and set the pixel value of a non-mark position pixel point as a second pixel value;
and accumulating pixel values of pixel points of the images in the initial image group, defining the pixel points with the accumulated pixel values larger than the preset pixel values as the pixel points with the road signs, and generating an initial road sign segmentation graph based on all the pixel points with the road signs.
10. A computer-readable storage medium, wherein the storage medium stores program instructions that, when executed, implement:
acquiring a monitoring video and extracting an initial image group in the monitoring video, wherein the initial image group comprises a preset number of images;
inputting the initial image group into a preset detection segmentation model so as to set the pixel value of a mark position pixel point of an image in the initial image group as a first pixel value and set the pixel value of a non-mark position pixel point as a second pixel value;
and accumulating pixel values of pixel points of the images in the initial image group, defining the pixel points with the accumulated pixel values larger than the preset pixel values as the pixel points with the road signs, and generating an initial road sign segmentation graph based on all the pixel points with the road signs.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110542215.6A CN113487688A (en) | 2021-05-18 | 2021-05-18 | Road sign detection method and device and computer readable storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110542215.6A CN113487688A (en) | 2021-05-18 | 2021-05-18 | Road sign detection method and device and computer readable storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113487688A true CN113487688A (en) | 2021-10-08 |
Family
ID=77932860
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110542215.6A Pending CN113487688A (en) | 2021-05-18 | 2021-05-18 | Road sign detection method and device and computer readable storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113487688A (en) |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2012104040A (en) * | 2010-11-12 | 2012-05-31 | Renesas Electronics Corp | Road recognition device and road recognition method |
| CN105718870A (en) * | 2016-01-15 | 2016-06-29 | 武汉光庭科技有限公司 | Road marking line extracting method based on forward camera head in automatic driving |
| CN109241984A (en) * | 2018-09-17 | 2019-01-18 | 暨南大学 | Tramway rubbish method for detecting position, computer installation and computer readable storage medium |
| CN109448000A (en) * | 2018-10-10 | 2019-03-08 | 中北大学 | A kind of dividing method of road sign image |
-
2021
- 2021-05-18 CN CN202110542215.6A patent/CN113487688A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2012104040A (en) * | 2010-11-12 | 2012-05-31 | Renesas Electronics Corp | Road recognition device and road recognition method |
| CN105718870A (en) * | 2016-01-15 | 2016-06-29 | 武汉光庭科技有限公司 | Road marking line extracting method based on forward camera head in automatic driving |
| CN109241984A (en) * | 2018-09-17 | 2019-01-18 | 暨南大学 | Tramway rubbish method for detecting position, computer installation and computer readable storage medium |
| CN109448000A (en) * | 2018-10-10 | 2019-03-08 | 中北大学 | A kind of dividing method of road sign image |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| EP3806064B1 (en) | Method and apparatus for detecting parking space usage condition, electronic device, and storage medium | |
| CN108986465B (en) | Method, system and terminal equipment for detecting traffic flow | |
| EP2858008A2 (en) | Target detecting method and system | |
| CN111583118B (en) | Image stitching method and device, storage medium and electronic equipment | |
| CN113112480B (en) | Video scene change detection method, storage medium and electronic device | |
| CN110114801B (en) | Image foreground detection device and method and electronic equipment | |
| US20220351413A1 (en) | Target detection method, computer device and non-transitory readable storage medium | |
| CN111553302B (en) | Key frame selection method, device, equipment and computer readable storage medium | |
| CN111402301B (en) | Water accumulation detection method and device, storage medium and electronic device | |
| CN111383246A (en) | Scroll detection method, device and equipment | |
| CN112927178B (en) | Occlusion detection method, occlusion detection device, electronic device, and storage medium | |
| CN115761655A (en) | Target tracking method and device | |
| CN112990009A (en) | End-to-end-based lane line detection method, device, equipment and storage medium | |
| CN113312949B (en) | Video data processing method, video data processing device and electronic equipment | |
| CN113487688A (en) | Road sign detection method and device and computer readable storage medium | |
| CN111310832A (en) | Picture duplicate checking method and system | |
| CN112801370B (en) | Water and soil loss prediction method, device, equipment and storage medium | |
| CN114821513A (en) | Image processing method and device based on multilayer network and electronic equipment | |
| CN112085002A (en) | Portrait segmentation method, portrait segmentation device, storage medium and electronic equipment | |
| CN104700396B (en) | The method and system of the parameter for estimating the volume of traffic is determined from image | |
| CN114926973B (en) | Video monitoring method, device, system, server and readable storage medium | |
| CN112020721A (en) | Training method and device for classification neural network for semantic segmentation, and electronic equipment | |
| CN115482478B (en) | Road identification method, device, unmanned aerial vehicle, equipment and storage medium | |
| CN115482477B (en) | Road identification method, device, unmanned aerial vehicle, equipment and storage medium | |
| CN112700657B (en) | Method and device for generating detection information, road side equipment and cloud control platform |
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 |