CN114022862A - Intelligent detection method and system for blocked traffic sign - Google Patents
Intelligent detection method and system for blocked traffic sign Download PDFInfo
- Publication number
- CN114022862A CN114022862A CN202111159648.XA CN202111159648A CN114022862A CN 114022862 A CN114022862 A CN 114022862A CN 202111159648 A CN202111159648 A CN 202111159648A CN 114022862 A CN114022862 A CN 114022862A
- Authority
- CN
- China
- Prior art keywords
- traffic sign
- target
- video
- road
- data
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Withdrawn
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
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)
Abstract
The application discloses an intelligent detection method and system for traffic sign sheltering, which are used for intelligent detection, so that pruning personnel can know the sheltered traffic sign and can prune the traffic sign, the consumption of manpower and material resources is reduced, and the economic cost is reduced. The method comprises the following steps: acquiring vehicle running video data and vehicle running positioning data; dividing vehicle running video data according to the vehicle running positioning data and generating at least one traffic sign video of the target road; carrying out image processing on a traffic sign video of a target road to generate a road image set; acquiring traffic sign data of a target road; determining a target image set with traffic sign data in a road image set; determining a set of the shielded rate of the target traffic sign in the traffic sign data according to the set of the target images; judging whether the minimum shielded rate in the shielded rate set of the target traffic sign is greater than a preset threshold value or not; and if so, generating a shielded notice according to the target traffic sign and the target road.
Description
Technical Field
The application relates to the technical field of traffic signs, in particular to an intelligent detection method and system for blocking of a traffic sign.
Background
The traffic sign board is a facility for transmitting specific information by using graphic symbols and characters to manage traffic and indicate driving direction to ensure smooth road and safe driving, is mainly suitable for highways, urban roads and all special highways, has the property of law, and is necessary to be observed by vehicles and pedestrians.
Urban afforestation refers to planting trees, flowers and plants in cities, and covering a certain ground or installing points. Along with the development of economy, urban greening attracts more and more attention as a reduction organization in an urban ecosystem, and the urban ecosystem has the capability of recovering from external interference and damage, such as: can hold dust, reduce noise, release oxygen and absorb harmful gas to purify air.
Along with the growth of trees, the branches and leaves of trees can be to the roadside overspread growth, and the traffic sign can be sheltered from to the branches and leaves that grow exuberantly, and when the traffic sign was sheltered from the certain degree, if can not in time manage, the driver could not see clearly or even can not see the traffic sign, can not in time make exact prejudgement according to the sign of traffic sign at the in-process of traveling to influence people's safety and road traffic safety. At present before pruning branches and leaves, mainly patrol the road through artifical periodicity, judge whether prune, but such mode need consume great manpower and materials, has increased economic cost.
Disclosure of Invention
The application provides an intelligent detection method and system for traffic sign sheltering, which are used for intelligent detection, so that pruning personnel can know the sheltered traffic sign and can prune the traffic sign in time, the consumption of manpower and material resources is reduced, and the economic cost is reduced.
The application provides an intelligent detection method for traffic sign sheltered, which comprises the following steps:
acquiring vehicle running video data and vehicle running positioning data, wherein the vehicle running video data is road information shot by a vehicle in the running process, and the vehicle running positioning data is running track information of the vehicle in the running process;
dividing the vehicle running video data according to the vehicle running positioning data and generating at least one traffic sign video of a target road, wherein the traffic sign video represents a section of video containing a traffic sign in the vehicle running video data;
performing image processing on the traffic sign video of the target road to generate a road image set;
acquiring traffic sign data of the target road;
determining a target image set with the traffic sign data in the road image set;
determining a set of shielded rates of the target traffic sign in the traffic sign data according to the set of target images;
judging whether the minimum shielded rate in the shielded rate set of the target traffic sign is greater than a preset threshold value or not;
and if so, generating a shielded notification according to the target traffic sign and the target road.
Optionally, the image processing the traffic sign video of the target road, and generating a road image set includes:
and performing image framing processing, gray image conversion processing, image dimension reduction processing and image histogram equalization processing on the traffic sign video of the target road, and generating a road image set.
Optionally, after the dividing and generating the traffic sign video of at least one target road for the vehicle driving video data according to the vehicle driving positioning data, before the image processing is performed on the traffic sign video of the target road and a road image set is generated, the intelligent detection method further includes:
dividing the vehicle running video data according to the vehicle running positioning data to generate a traffic video;
and performing road identification on the traffic video to generate at least one traffic sign video of the target road.
Optionally, the determining the set of occluded rates of the target traffic sign in the traffic sign data from the set of target images comprises:
extracting green plant features in the target image set;
calculating the shielded rate of the target image set according to the green plant characteristics to generate a shielded rate data set;
and determining the shielded rate set of the target traffic sign in the traffic sign data according to the shielded rate data set.
Optionally, after generating the blocked notification according to the target traffic sign and the target road if the detected traffic sign is located, the intelligent detection method further includes:
acquiring an occluded image set of a target traffic sign and a historical occluded image set of the target traffic sign;
comparing the shielded image set of the target traffic sign with the historical shielded image set of the target traffic sign;
and when the occluded area of the occluded image set of the target traffic sign is smaller than the occluded area of the historical occluded image set, updating the traffic sign data of the target traffic sign in the database.
This application second aspect provides an intelligent detecting system that traffic sign is sheltered from, includes:
the vehicle driving positioning data is the driving track information of the vehicle in the driving process;
the first generation unit is used for dividing the vehicle running video data according to the vehicle running positioning data and generating at least one traffic sign video of a target road, wherein the traffic sign video represents a section of video containing a traffic sign in the vehicle running video data;
the second generation unit is used for carrying out image processing on the traffic sign video of the target road to generate a road image set;
a second acquisition unit configured to acquire traffic sign data of the target road;
a first determination unit configured to determine a target image set including the traffic sign data from among the road image set;
the second determining unit is used for determining the shielded rate set of the target traffic sign in the traffic sign data according to the target image set;
the judging unit is used for judging whether the minimum shielded rate in the shielded rate set of the target traffic sign is greater than a preset threshold value or not;
and the third generating unit is used for generating an occluded notification according to the target traffic sign and the target road if the minimum occluded rate in the occluded rate set of the target traffic sign is greater than a preset threshold value.
Optionally, the second generating unit is specifically configured to perform image framing processing, grayscale image conversion processing, image dimension reduction processing, and image histogram equalization processing on the traffic sign video of the target road, and generate a road image set.
Optionally, the intelligent detection system further includes:
the fourth generating unit is used for dividing the vehicle running video data according to the vehicle running positioning data so as to generate a traffic video;
and the identification unit is used for carrying out road identification on the traffic video so as to generate at least one traffic sign video of the target road.
Optionally, the second determining unit is specifically configured to extract a green plant feature in the target image set;
calculating the shielded rate of the target image set according to the green plant characteristics to generate a shielded rate data set;
and determining the shielded rate set of the target traffic sign in the traffic sign data according to the shielded rate data set.
Optionally, the intelligent detection system further includes:
the third acquisition unit is used for acquiring the shielded image set of the target traffic sign and the historical shielded image set of the target traffic sign;
the comparison unit is used for comparing the shielded image set of the target traffic sign with the historical shielded image set of the target traffic sign;
and the updating unit is used for updating the traffic sign data of the target traffic sign in the database when the blocked area of the blocked image set of the target traffic sign is smaller than the blocked area of the historical blocked image set.
A third aspect of the present application provides an intelligent detection system for traffic sign being blocked, comprising:
the system comprises a central processing unit, a memory, an input/output interface, a wired or wireless network interface and a power supply;
the memory is a transient memory or a persistent memory;
the central processor is configured to communicate with the memory and to execute the operations of the instructions in the memory to perform the method of any one of the first aspect of the method and alternatives of the first aspect.
A fourth aspect of the present application provides a computer-readable storage medium comprising instructions which, when executed on a computer, cause the computer to perform the method of any one of the first aspect of the aforementioned method and alternatives of the first aspect.
According to the technical scheme, the method has the following beneficial effects:
in the application, a system acquires vehicle running video data and vehicle running positioning data, the vehicle running video data is road information shot by a vehicle in the running process, the vehicle running positioning data is running track information of the vehicle in the running process, the vehicle running video data is divided and generated into at least one traffic sign video of a target road according to the vehicle running positioning data, the traffic sign video represents a section of video containing a traffic sign in the vehicle running video data, the traffic sign video of the target road is subjected to image processing to generate a road image set, the traffic sign data of the target road is acquired, a target image set with the traffic sign data in the road image set is determined, the shielded rate set of the target traffic sign in the traffic sign data is determined according to the target image set, and whether the minimum shielded rate in the shielded rate set of the target traffic sign is greater than a preset threshold value or not is judged, and if so, generating a shielded notice according to the target traffic sign and the target road. According to the scheme, manual patrol is not needed, and system intelligent detection is adopted, so that pruning personnel can know the sheltered traffic sign in time and prune in time, consumption of manpower and material resources is reduced, and economic cost is reduced.
Drawings
FIG. 1 is a schematic diagram of an intelligent method for detecting traffic sign blocking according to the present application;
FIGS. 2-1 and 2-2 are schematic diagrams of another intelligent detection method for traffic sign blocking according to the present application;
FIG. 3 is a schematic view of an intelligent detection system for traffic signs being obscured according to the present application;
FIG. 4 is another schematic view of an intelligent detection system for blocking a traffic sign according to the present application;
FIG. 5 is another schematic diagram of an intelligent detection system for blocking a traffic sign according to the present application.
Detailed Description
In order to make those skilled in the art better understand the technical solution of the present invention, the technical solution in the embodiment of the present invention will be clearly and completely described below with reference to the drawings in the embodiment of the present invention, and it is obvious that the described embodiment is only a part of the embodiment of the present invention, and not all embodiments. All other embodiments, which can be obtained by a person skilled in the art without any inventive step based on the embodiments of the present invention, shall fall within the scope of the present invention.
The intelligent detection method for the traffic sign blocking can be applied to a system and can also be applied to a server. For convenience of explanation, the system is taken as an implementation subject in the present application for illustration.
The application provides an intelligent detection method and system for traffic sign sheltering, which are used for intelligent detection, so that pruning personnel can know the sheltered traffic sign and can prune the traffic sign in time, the consumption of manpower and material resources is reduced, and the economic cost is reduced.
Referring to fig. 1, fig. 1 is a schematic flowchart illustrating an embodiment of an intelligent method for detecting traffic sign blocking according to the present application, where the method for detecting traffic sign blocking comprises:
101. acquiring vehicle running video data and vehicle running positioning data;
in this embodiment, the car networking refers to connecting cars together to form a network. The automobile and the automobile form an automobile network, the automobile network is connected with the Internet, and the automobile network, the automobile network and the Internet are based on a unified protocol to realize data intercommunication among people, the automobile, the road and the cloud and finally realize functions of intelligent transportation, intelligent automobile intelligent driving and the like. The system obtains vehicle driving video data and vehicle driving positioning data through the internet of vehicles, the vehicle driving video data is road information shot by a vehicle in the driving process, and the vehicle driving positioning data is driving track information of the vehicle in the driving process, for example: when the vehicle travels from the a ground to the B ground, and the distance from the a ground to the B ground is 25 km, the vehicle travel video data includes information data such as a passing pedestrian, a vehicle, architectural greening on both sides of a road, and a traffic sign on the road, which are captured by the vehicle traveling from the a ground to the B ground one road, and the vehicle travel positioning data includes track information of the road on which the vehicle travels from the a ground to the B ground since the road is not a straight distance in an ideal state. The vehicle driving positioning data and the vehicle driving video data are acquired in order to divide the vehicle driving video data and generate a traffic sign video of a target road according to the vehicle driving positioning data, which is described in detail below.
In this embodiment, the vehicle driving video data may be captured by a vehicle-mounted camera or a vehicle event data recorder, and is not limited herein.
The vehicle driving positioning data in this embodiment may be obtained through a global positioning system, or may be obtained through a combined positioning of a global positioning system and a dead reckoning system, which is not limited herein.
102. Dividing vehicle running video data according to the vehicle running positioning data and generating at least one traffic sign video of the target road;
in this embodiment, after the vehicle driving video data and the vehicle driving positioning data are obtained, the system divides and generates at least one traffic sign video of the target road for the vehicle driving video data according to the vehicle driving positioning data, the traffic sign video represents a section of video containing a traffic sign in the vehicle driving video data, and the larger the vehicle driving positioning data is, the larger the number of the divided and generated traffic sign videos is. For example: the driving distance of the target vehicle from the ground B to the ground C is 15 kilometers, the vehicle driving positioning data of the target vehicle is 15 kilometers of the driving of the target vehicle, the vehicle driving video data comprise all information data shot by the target vehicle from the ground B to the road C passing through, the vehicle driving video data are divided into 5 traffic sign videos according to the vehicle driving positioning data of 15 kilometers, and the vehicle track distance in each traffic sign video is 3 kilometers.
The vehicle driving positioning data in this embodiment may be 20 kilometers or 25 kilometers, and is not limited herein.
103. Carrying out image processing on a traffic sign video of a target road to generate a road image set;
in this embodiment, after dividing the vehicle driving video data according to the vehicle driving positioning data and generating the traffic sign video of at least one target road, since the traffic sign video is obtained by dividing the vehicle driving video data, and the vehicle driving video data is obtained by the camera when the vehicle is driving on the road, the obtained driving video has situations of unclear picture, missing image in the picture, etc., in order to obtain a clear and effective video for subsequently determining the blocked rate of the traffic sign, after the traffic sign video is generated, the system needs to perform image processing on the traffic sign video and generate a road image set, and mainly performs image framing processing, grayscale image conversion processing, image dimension reduction processing, and image histogram equalization processing on the traffic sign video of the target road, a specific implementation step is performed, will be explained in the following examples.
104. Acquiring traffic sign data of a target road;
in this embodiment, the traffic sign set on each road has information corresponding to the traffic sign recorded in the database, and after the road image set is generated, the system acquires traffic sign data of the target road from the database, where the traffic sign data includes position information of a traffic sign on the target road, a history blocked image set, and a history blocked rate set, for example: the system comprises a first target road, a second target road, a third target road, a fourth target road and a fourth target road, wherein the first target road is provided with a first traffic sign and a second traffic sign, the system acquires traffic sign data of the first traffic sign and the second traffic sign on the first target road from a database, and the traffic sign data of the first traffic sign comprises first position information of the first traffic sign, a history shielded image set consisting of three shielded images and a history shielded rate set consisting of 51%, 43% and 26% of shielded rate; the traffic sign data of the second traffic sign includes the second-position information where the second traffic sign is located, a history occluded image set composed of four occluded images, and a history occluded rate set composed of occluded rates of 22%, 35%, 42%, and 46%. The traffic sign data of the target road is acquired, and the target image set in the road image set is mainly determined according to the traffic sign data, which is specifically described below.
105. Determining a target image set with traffic sign data in a road image set;
in this embodiment, after image processing is performed on a traffic sign video of a target road, if some road images in a generated road image set have traffic signs, and some road images do not have traffic signs, and the road images without traffic signs are not images required in the scheme, the redundant images are removed, that is, the road images without traffic signs do not exist; and inducing and integrating the road images with the traffic signs to generate an image set, namely a target image set, wherein the image set of each traffic sign generates a corresponding target image set. For example: the driving distance of the target vehicle from the ground B to the ground C is 15 kilometers, the target vehicle is divided into 5 traffic sign videos according to the driving positioning data of the vehicle of 15 kilometers, the traffic sign videos on the first target road are converted into a road image set consisting of five images a1, B1, C1, d1 and e1, wherein the images a1, B1 and C1 have a traffic sign, the images d1 and e1 do not have the traffic sign, the images d1 and e1 are removed, and the images a1, B1 and C1 are generated into a target image set of the traffic sign.
106. Determining a set of the shielded rate of the target traffic sign in the traffic sign data according to the set of the target images;
in this embodiment, after determining a target image set having traffic sign data in a road image set, a system determines, according to the target image set, an occlusion rate set of a target traffic sign in the traffic sign data, where the occlusion rate set is a set obtained by shooting the target traffic sign from far to near in a driving process of a target vehicle and calculating an area of the traffic sign occluded by branches and leaves in each image, and each traffic sign has a corresponding occlusion rate set in the traffic sign data.
107. Judging whether the minimum shielded rate in the shielded rate set of the target traffic sign is greater than a preset threshold value or not;
in this embodiment, after determining the set of the blocked rates of the target traffic sign in the traffic sign data, the system screens the data in the set of the blocked rates of the target traffic sign, selects the minimum blocked rate of the data, and determines whether the minimum blocked rate is greater than a preset threshold value, so as to determine whether to trim branches and leaves of the traffic sign, when the target vehicle is closer to the target traffic sign in the driving process, the larger the blocked rate of the acquired image is, when the minimum blocked rate is greater than the preset threshold value, it indicates that trimming needs to be performed, and otherwise, when the minimum blocked rate is less than the preset threshold value, trimming does not need to be performed. For example: the preset threshold value of the blocked rate is 35%, the blocked rates of the third target traffic sign are 45%, 37% and 20%, respectively, and the minimum blocked rate of 20% is less than the preset threshold value of the blocked rate of 35%, so that the third target traffic sign does not need to be trimmed; the sheltered rate of the fourth target traffic sign is 55%, 47% and 38%, respectively, and the minimum sheltered rate 38% is greater than the preset threshold of sheltered rate and is 35%, then the fourth target traffic sign needs to be trimmed.
In this embodiment, the preset threshold of the blocked rate may be 30% or 40%, and is not limited herein.
108. And if the minimum shielded rate in the shielded rate set of the target traffic sign is greater than a preset threshold value, generating a shielded notification according to the target traffic sign and the target road.
In this embodiment, when it is determined that the minimum blocked rate in the blocked rate set of the target traffic sign is greater than the preset threshold, the system generates a blocked notification according to the target traffic sign and the target road, where the blocked notification includes the name of the target road, the position information of the target traffic sign, and the blocked rate of the target traffic sign, and sends the notification to the control room, so that a pruner knows that the blocked area of the target traffic sign is large, and in order to reduce a safety accident caused by a driver being unable to make an accurate prediction due to the traffic sign being blocked by a branch and a leaf, the pruner timely goes to the target road according to the name of the target road, the position information of the target traffic sign, and the blocked rate of the target traffic sign in the blocked notification, and prunes the branch and the leaf of the target traffic sign. Before pruning branches and leaves, the system does not need to inspect roads regularly by manpower, but detects roads by the system, reduces the consumption of manpower and material resources, and reduces the economic cost.
In the embodiment, the system acquires vehicle driving video data and vehicle driving positioning data, the vehicle driving video data is road information shot by a vehicle in the driving process, the vehicle driving positioning data is driving track information of the vehicle in the driving process, the vehicle driving video data is divided and generated into at least one traffic sign video of a target road according to the vehicle driving positioning data, the traffic sign video represents a section of video containing a traffic sign in the vehicle driving video data, the traffic sign video of the target road is subjected to image processing to generate a road image set, the traffic sign data of the target road is acquired, a target image set with the traffic sign data in the road image set is determined, the shielded rate set of the target traffic sign in the traffic sign data is determined according to the target image set, and whether the minimum shielded rate in the shielded rate set of the target traffic sign is greater than a preset threshold value or not is judged, and if so, generating a shielded notice according to the target traffic sign and the target road. According to the scheme, manual patrol is not needed, and system intelligent detection is adopted, so that pruning personnel can know the sheltered traffic sign in time and prune in time, consumption of manpower and material resources is reduced, and economic cost is reduced.
Referring to fig. 2-1 and 2-2, fig. 2-1 and 2-2 are schematic flow charts of another embodiment of the intelligent method for detecting traffic sign occlusion provided by the present application, where the method for detecting traffic sign occlusion comprises:
201. acquiring vehicle running video data and vehicle running positioning data;
202. dividing vehicle running video data according to the vehicle running positioning data and generating at least one traffic sign video of the target road;
203. Dividing vehicle running video data according to the vehicle running positioning data to generate a traffic video;
204. performing road identification on the traffic video to generate a traffic sign video of at least one target road;
in this embodiment, vehicle driving positioning data is the track information of going of vehicle in the course of going, when the vehicle has long distance track of going, the system divides the multistage video for vehicle driving video data according to this vehicle driving positioning data, in order to generate the traffic video of a plurality of subsections, include the video data that corresponds among the vehicle driving video data in this traffic video, carry out the sign of road name and road position to each section traffic video that generates again, thereby generate corresponding traffic sign video, each section traffic sign video all has corresponding road name and road position, so that pruner can know this road name and road position that corresponds according to this traffic sign video. For example: the distance of traveling in the vehicle driving positioning data is 40 kilometers, there is this 40 kilometers video of traveling in the vehicle video data of traveling, set up one section traffic video of every 8 kilometers divisions, then divide the distance of traveling for 40 kilometers and generate 5 sections traffic videos, carry out the road sign to these 5 sections traffic videos again, 1 st section traffic video sign is first traffic sign video, 2 nd section traffic video sign is second traffic sign video, 3 rd section traffic video sign is third traffic sign video, 4 th section traffic video sign is fourth traffic sign video, 5 th section traffic video sign is fifth traffic sign video.
205. Carrying out image framing processing, gray level image conversion processing, image dimension reduction processing and image histogram equalization processing on a traffic sign video of a target road, and generating a road image set;
in this embodiment, after dividing the vehicle driving video data according to the vehicle driving positioning data and generating the traffic sign video of at least one target road, because the traffic sign video is obtained by dividing the vehicle driving video data, and the vehicle driving video data is obtained by a camera when a vehicle drives on a road, the obtained driving video has situations of unclear picture, missing image in the picture, and the like, and the system performs image framing processing, grayscale image conversion processing, image dimension reduction processing, and image histogram equalization processing on the traffic sign video of the target road. The traffic sign video has certain continuity, and if a target traffic sign in the whole video and a green feature on the target traffic sign are extracted, the detection result is easy to be inaccurate, so that the traffic sign video needs to be subjected to image framing processing, namely, the video is converted into a frame image set, a total frame number of the traffic sign video is mainly inquired, the traffic sign video is divided into a plurality of frame images based on the total frame number, and the plurality of frame images are converted into an image format, so that the frame image set is obtained, each frame image in the video is accurately detected, the detection accuracy is improved, and the accuracy of a blocked rate calculation result is improved. The gray level image conversion processing generates a grid matrix image, namely the data type of the image is a matrix, and the grid matrix image is a monochromatic gray level image. And then performing image dimensionality reduction on the image after the gray level image conversion processing to obtain a monochrome image so as to construct a data set. And finally, reducing the influence of illumination through image histogram equalization processing.
206. Acquiring traffic sign data of a target road;
207. determining a target image set with traffic sign data in a road image set;
208. Extracting green plant characteristics in the target image set;
209. calculating the shielded rate of the target image set according to the green plant characteristics to generate a shielded rate data set;
210. determining an occluded rate set of the target traffic sign in the traffic sign data according to the occluded rate data set;
in this embodiment, after determining a target image set including traffic sign data in a road image set, the system extracts a green plant feature of each image in the target image set, calculates an occlusion rate of the image according to an area ratio of the green plant feature in a corresponding image, calculates each target image in the target image set including the green plant feature, generates an occlusion rate data set of the target traffic sign, and determines an occlusion rate set of the target traffic sign in the traffic sign data according to the occlusion rate data set. For example: the third traffic sign and the fourth traffic sign are arranged on the second target road, the target vehicle shoots three images of a2, b2 and c2 on the third traffic sign in the driving process to generate a third target image set, green plant extraction is carried out on the three images of the third target image set to calculate the blocked rates to be 45%, 37% and 20% respectively, the three blocked rates generate a blocked rate set of the third target traffic sign, the three images of a3, b3 and c3 are shot on the fourth traffic sign to generate a fourth target image set, the three images in the fourth target image set are calculated to obtain the blocked rates to be 55%, 47% and 38% respectively, and the three blocked rates generate a blocked rate set of the fourth target traffic sign.
211. Judging whether the minimum shielded rate in the shielded rate set of the target traffic sign is greater than a preset threshold value or not;
212. if the minimum shielded rate in the shielded rate set of the target traffic sign is greater than a preset threshold value, generating a shielded notification according to the target traffic sign and the target road;
213. Acquiring an occluded image set of a target traffic sign and a historical occluded image set of the target traffic sign;
214. comparing the shielded image set of the target traffic sign with the historical shielded image set of the target traffic sign;
215. and when the occluded area of the occluded image set of the target traffic sign is smaller than the occluded area of the historical occluded image set, updating the traffic sign data of the target traffic sign in the database.
In the present embodiment, after generating the notification of being occluded from the target traffic sign and the target road, and sending the notification to the control room, the system acquires an occluded image set of the target traffic sign and a historical occluded image set of the target traffic sign, extracting green plant features in the image to determine branches and leaves in the image, comparing the occluded image set of the target traffic sign with the historical occluded image set of the target traffic sign, when the occluded area of the occluded image set of the target traffic sign is smaller than the occluded area of the historical occluded image set, indicating that the branches and leaves of the target traffic sign have been processed by the pruner, the system updates the traffic sign data for the target traffic sign in the database, i.e., updates the trimmed image set of the target traffic sign to the latest historical occluded image set.
In the embodiment, the system acquires vehicle running video data and vehicle running positioning data, divides the vehicle running video data according to the vehicle running positioning data and generates at least one traffic sign video of a target road, divides the vehicle running video data according to the vehicle running positioning data to generate a traffic video, performs road marking on the traffic video to generate at least one traffic sign video of the target road, performs image framing processing, grayscale image conversion processing, image dimension reduction processing and image histogram equalization processing on the traffic sign video of the target road, generates a road image set, acquires the traffic sign data of the target road, determines a target image set with the traffic sign data in the road image set, extracts green planting features in the target image set, calculates the blocked rate of the target image set according to the green planting features, and generating an occluded rate data set, determining an occluded rate set of the target traffic sign in the traffic sign data according to the occluded rate data set, judging whether the minimum occluded rate in the occluded rate set of the target traffic sign is greater than a preset threshold value, and if so, generating an occluded notification according to the target traffic sign and the target road. According to the scheme, manual patrol is not needed, and system intelligent detection is adopted, so that pruning personnel can know the sheltered traffic sign in time and prune in time, consumption of manpower and material resources is reduced, and economic cost is reduced. The system acquires an occluded image set of the target traffic sign and a historical occluded image set of the target traffic sign, compares the occluded image set of the target traffic sign with the historical occluded image set of the target traffic sign, updates the trimmed image set of the target traffic sign to a latest historical occluded image set when the occluded area of the occluded image set of the target traffic sign is smaller than the occluded area of the historical occluded image set, and calculates according to the latest historical occluded image set when the occluded rate is calculated next time.
Referring to fig. 3, fig. 3 is a schematic flowchart illustrating an embodiment of an intelligent traffic sign blocking detection system provided in the present application, where the intelligent traffic sign blocking detection system includes:
a first obtaining unit 301, configured to obtain vehicle driving video data and vehicle driving positioning data, where the vehicle driving video data is road information captured by a vehicle during driving, and the vehicle driving positioning data is driving track information of the vehicle during driving;
a first generating unit 302, configured to divide and generate at least one traffic sign video of a target road for vehicle driving video data according to vehicle driving location data, where the traffic sign video represents a segment of video containing a traffic sign in the vehicle driving video data;
a second generating unit 303, configured to perform image processing on the traffic sign video of the target road to generate a road image set;
a second acquisition unit 304 for acquiring traffic sign data of the target road;
a first determination unit 305 configured to determine a target image set including traffic sign data among the road image set;
a second determining unit 306, configured to determine a set of blocked rates of the target traffic sign in the traffic sign data according to the set of target images;
the judging unit 307 is configured to judge whether the minimum blocked rate in the blocked rate set of the target traffic sign is greater than a preset threshold;
a third generating unit 308, configured to generate an occluded notification according to the target traffic sign and the target road if the minimum occluded rate in the occluded rate set of the target traffic sign is greater than a preset threshold.
Referring to fig. 4, fig. 4 is a schematic flowchart illustrating another embodiment of the intelligent traffic sign blocking detection system provided in the present application, where the intelligent traffic sign blocking detection system includes:
a first obtaining unit 401, configured to obtain vehicle driving video data and vehicle driving positioning data, where the vehicle driving video data is road information captured by a vehicle during driving, and the vehicle driving positioning data is driving track information of the vehicle during driving;
a first generating unit 402, configured to divide and generate at least one traffic sign video of a target road for vehicle driving video data according to vehicle driving location data, where the traffic sign video represents a segment of video containing a traffic sign in the vehicle driving video data;
a second generating unit 403, configured to divide the vehicle driving video data according to the vehicle driving location data to generate a traffic video;
an identification unit 404, configured to perform road identification on the traffic video to generate a traffic sign video of at least one target road;
a third generating unit 405, configured to perform image framing processing, grayscale image conversion processing, image dimension reduction processing, and image histogram equalization processing on the traffic sign video of the target road, and generate a road image set;
a second acquiring unit 406 for acquiring traffic sign data of the target road;
a first determination unit 407 configured to determine a target image set including traffic sign data in the road image set;
an extracting unit 408, configured to extract a green plant feature in the target image set;
a fourth generating unit 409, configured to calculate an occluded rate of the target image set according to the green plant characteristics, and generate an occluded rate data set;
a second determining unit 410, configured to determine a set of occluded rates of the target traffic sign in the traffic sign data according to the set of occluded rates;
the determining unit 411 is configured to determine whether the minimum blocked rate in the blocked rate set of the target traffic sign is greater than a preset threshold;
a fifth generating unit 412, configured to generate a blocked notification according to the target traffic sign and the target road if the minimum blocked rate in the blocked rate set of the target traffic sign is greater than a preset threshold;
a third acquiring unit 413 for acquiring an occluded image set of the target traffic sign and a history occluded image set of the target traffic sign;
a comparing unit 414, configured to compare the occluded image set of the target traffic sign with the historical occluded image set of the target traffic sign;
the updating unit 415 updates the traffic sign data of the target traffic sign in the database when the occluded area of the occluded image set of the target traffic sign is smaller than the occluded area of the history occluded image set.
Referring to fig. 5, fig. 5 is a schematic flowchart illustrating another embodiment of the intelligent traffic sign blocking detection system according to the present application, where the intelligent traffic sign blocking detection system includes:
a central processing unit 502, a memory 501, an input/output interface 503, a wired or wireless network interface 504 and a power supply 505;
the memory 501 is a transient storage memory or a persistent storage memory;
the central processor 502 is configured to communicate with the memory 501 and execute the operations of the instructions in the memory 501 to perform the steps described in the embodiments of fig. 1, 2-1, and 2-2.
The present application provides a computer-readable storage medium comprising instructions that, when executed on a computer, cause the computer to perform method embodiments corresponding to the embodiment of fig. 1 or the embodiments of fig. 2-1 and 2-2.
It is clear to those skilled in the art that, for convenience and brevity of description, the specific working processes of the above-described systems, apparatuses and units may refer to the corresponding processes in the foregoing method embodiments, and are not described herein again.
In the several embodiments provided in the present application, it should be understood that the disclosed system, apparatus and method may be implemented in other manners. For example, the above-described apparatus embodiments are merely illustrative, and for example, the division of the units is only one logical division, and other divisions may be realized in practice, 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.
The 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 solution 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 server, or a network device) to execute all or part of the steps of the method according to the embodiments of the present application. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a read-only memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, and various other media capable of storing program codes.
Claims (10)
1. An intelligent detection method for the sheltered traffic sign is characterized by comprising the following steps:
acquiring vehicle running video data and vehicle running positioning data, wherein the vehicle running video data is road information shot by a vehicle in the running process, and the vehicle running positioning data is running track information of the vehicle in the running process;
dividing the vehicle running video data according to the vehicle running positioning data and generating at least one traffic sign video of a target road, wherein the traffic sign video represents a section of video containing a traffic sign in the vehicle running video data;
performing image processing on the traffic sign video of the target road to generate a road image set;
acquiring traffic sign data of the target road;
determining a target image set with the traffic sign data in the road image set;
determining a set of shielded rates of the target traffic sign in the traffic sign data according to the set of target images;
judging whether the minimum shielded rate in the shielded rate set of the target traffic sign is greater than a preset threshold value or not;
and if so, generating a shielded notification according to the target traffic sign and the target road.
2. The intelligent detection method according to claim 1, wherein the image processing the traffic sign video of the target road to generate a road image set comprises:
and performing image framing processing, gray image conversion processing, image dimension reduction processing and image histogram equalization processing on the traffic sign video of the target road, and generating a road image set.
3. The intelligent detection method according to claim 1, wherein after the dividing and generating the traffic sign video of at least one target road for the vehicle driving video data according to the vehicle driving positioning data, before the image processing the traffic sign video of the target road to generate the road image set, the intelligent detection method further comprises:
dividing the vehicle running video data according to the vehicle running positioning data to generate a traffic video;
and performing road identification on the traffic video to generate at least one traffic sign video of the target road.
4. The intelligent detection method of claim 1, wherein the determining the set of occlusion rates for the target traffic sign in the traffic sign data from the set of target images comprises:
extracting green plant features in the target image set;
calculating the shielded rate of the target image set according to the green plant characteristics to generate a shielded rate data set;
and determining the shielded rate set of the target traffic sign in the traffic sign data according to the shielded rate data set.
5. The intelligent detection method according to any one of claims 1 to 4, wherein after the if, generating an obstructed notification according to the target traffic sign and the target road, the intelligent detection method further comprises:
acquiring an occluded image set of a target traffic sign and a historical occluded image set of the target traffic sign;
comparing the shielded image set of the target traffic sign with the historical shielded image set of the target traffic sign;
and when the occluded area of the occluded image set of the target traffic sign is smaller than the occluded area of the historical occluded image set, updating the traffic sign data of the target traffic sign in the database.
6. An intelligent detection system for traffic sign occlusion, comprising:
the vehicle driving positioning data is the driving track information of the vehicle in the driving process;
the first generation unit is used for dividing the vehicle running video data according to the vehicle running positioning data and generating at least one traffic sign video of a target road, wherein the traffic sign video represents a section of video containing a traffic sign in the vehicle running video data;
the second generation unit is used for carrying out image processing on the traffic sign video of the target road to generate a road image set;
a second acquisition unit configured to acquire traffic sign data of the target road;
a first determination unit configured to determine a target image set including the traffic sign data from among the road image set;
the second determining unit is used for determining the shielded rate set of the target traffic sign in the traffic sign data according to the target image set;
the judging unit is used for judging whether the minimum shielded rate in the shielded rate set of the target traffic sign is greater than a preset threshold value or not;
and the third generating unit is used for generating an occluded notification according to the target traffic sign and the target road if the minimum occluded rate in the occluded rate set of the target traffic sign is greater than a preset threshold value.
7. The intelligent detection system for the traffic sign shielding is characterized in that the second generation unit specifically comprises:
and performing image framing processing, gray image conversion processing, image dimension reduction processing and image histogram equalization processing on the traffic sign video of the target road, and generating a road image set.
8. An intelligent detection system for traffic signs being obscured, the intelligent detection system further comprising: the fourth generating unit is used for dividing the vehicle running video data according to the vehicle running positioning data so as to generate a traffic video;
and the identification unit is used for carrying out road identification on the traffic video so as to generate at least one traffic sign video of the target road.
9. An intelligent detection system for traffic sign sheltered is characterized in that the second determination unit specifically is:
extracting green plant features in the target image set;
calculating the shielded rate of the target image set according to the green plant characteristics to generate a shielded rate data set;
and determining the shielded rate set of the target traffic sign in the traffic sign data according to the shielded rate data set.
10. An intelligent detection system for traffic sign occlusion, comprising:
the system comprises a central processing unit, a memory, an input/output interface, a wired or wireless network interface and a power supply;
the memory is a transient memory or a persistent memory;
the central processor is configured to communicate with the memory and execute the operations of the instructions in the memory to perform the method of any of claims 1 to 5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111159648.XA CN114022862A (en) | 2021-09-30 | 2021-09-30 | Intelligent detection method and system for blocked traffic sign |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111159648.XA CN114022862A (en) | 2021-09-30 | 2021-09-30 | Intelligent detection method and system for blocked traffic sign |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114022862A true CN114022862A (en) | 2022-02-08 |
Family
ID=80055393
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111159648.XA Withdrawn CN114022862A (en) | 2021-09-30 | 2021-09-30 | Intelligent detection method and system for blocked traffic sign |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114022862A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114792471A (en) * | 2022-04-25 | 2022-07-26 | 南京泛在地理信息产业研究院有限公司 | Intelligent city traffic management early warning system based on GIS platform |
| WO2024087290A1 (en) * | 2022-10-26 | 2024-05-02 | 中公高科养护科技股份有限公司 | Road sign and security protection facility loss detection method and system, and medium |
-
2021
- 2021-09-30 CN CN202111159648.XA patent/CN114022862A/en not_active Withdrawn
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114792471A (en) * | 2022-04-25 | 2022-07-26 | 南京泛在地理信息产业研究院有限公司 | Intelligent city traffic management early warning system based on GIS platform |
| WO2024087290A1 (en) * | 2022-10-26 | 2024-05-02 | 中公高科养护科技股份有限公司 | Road sign and security protection facility loss detection method and system, and medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108345822B (en) | Point cloud data processing method and device | |
| CN104851295A (en) | Method and system for acquiring road condition information | |
| US20150178572A1 (en) | Road surface condition classification method and system | |
| CN111209780A (en) | Lane line attribute detection method and device, electronic device and readable storage medium | |
| CN114022862A (en) | Intelligent detection method and system for blocked traffic sign | |
| CN108460968A (en) | A kind of method and device obtaining traffic information based on car networking | |
| CN110188482B (en) | Test scene creating method and device based on intelligent driving | |
| CN105702152A (en) | Map generation method and device | |
| CN103927886A (en) | System and method for monitoring illegal speeding of key transport vehicle | |
| DE102017115197A1 (en) | GENERATION OF VIRTUAL SENSOR DATA FOR COLLECTING BOLLARS | |
| CN111209777A (en) | Lane line detection method and device, electronic device and readable storage medium | |
| CN112633722B (en) | Vehicle-mounted road safety risk assessment system and method | |
| CN109523787A (en) | A kind of fatigue driving analysis method based on vehicle pass-through track | |
| CN113255439B (en) | Obstacle identification method, device, system, terminal and cloud | |
| CN104157160A (en) | Vehicle drive control method and device as well as vehicle | |
| CN109920266A (en) | A kind of intelligent vehicle localization method | |
| WO2024046053A1 (en) | Vehicle violation detection method, apparatus and system, and storage medium | |
| CN109191492A (en) | A kind of intelligent video black smoke vehicle detection method based on edge analysis | |
| TW201719541A (en) | Method and system of analyzing and predicting high-risk road section by means of driving behavior utilizing an on-board unit to collect a driver's driving trajectory for analyzing bad driving behaviors and therefore learn a high-risk road section | |
| CN110782653A (en) | Road information acquisition method and system | |
| CN109948419A (en) | A kind of illegal parking automatic auditing method based on deep learning | |
| CN115546742A (en) | Rail foreign matter identification method and system based on monocular thermal infrared camera | |
| CN114771548A (en) | Data logging for advanced driver assistance system testing and verification | |
| CN112418081B (en) | Method and system for quickly surveying traffic accidents by air-ground combination | |
| CN113408319A (en) | Urban road abnormity perception processing method, device, system 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 | ||
| WW01 | Invention patent application withdrawn after publication |
Application publication date: 20220208 |
|
| WW01 | Invention patent application withdrawn after publication |