CN111461024B - Zombie vehicle identification method based on intelligent vehicle-mounted terminal - Google Patents
Zombie vehicle identification method based on intelligent vehicle-mounted terminal Download PDFInfo
- Publication number
- CN111461024B CN111461024B CN202010253041.7A CN202010253041A CN111461024B CN 111461024 B CN111461024 B CN 111461024B CN 202010253041 A CN202010253041 A CN 202010253041A CN 111461024 B CN111461024 B CN 111461024B
- Authority
- CN
- China
- Prior art keywords
- vehicle
- zombie
- executing
- roadside
- identification method
- 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.)
- Active
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/40—Scenes; Scene-specific elements in video content
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/60—Analysis of geometric attributes
- G06T7/62—Analysis of geometric attributes of area, perimeter, diameter or volume
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V2201/00—Indexing scheme relating to image or video recognition or understanding
- G06V2201/08—Detecting or categorising vehicles
Abstract
The application discloses a zombie vehicle identification method based on an intelligent vehicle-mounted terminal, which is characterized in that vehicles are identified from videos based on an image algorithm, the zombie vehicles are primarily judged by utilizing longitude and latitude, speed and a threshold value, finally, the zombie vehicles are identified by a deep learning technology and a locally learned vehicle image identification algorithm, and information of the zombie vehicles is reported to related departments by utilizing a blockchain technology, so that the problems can be timely processed. Thereby achieving the purpose of correspondingly improving the number of parking spaces and improving the appearance and environment of urban areas.
Description
Technical Field
The application relates to the field of big data analysis and data mining, in particular to a zombie vehicle identification method based on an intelligent vehicle-mounted terminal.
Background
With the development of society, the living standard of people is continuously improved, the quantity of motor vehicles is continuously increased, and the zombie vehicles in cities are parked for a long time and are not maintained by people, so that public resources such as roads and parking spaces are occupied for a long time, urban images are affected, and meanwhile, potential safety hazards such as spontaneous combustion and spontaneous explosion are also caused, the normal traffic of the roads is affected, and even some vehicles are leaked and pollute the environment due to the fact that the vehicles are parked for a long time. The city range is wide, the roads are many, the search of the zombie vehicle is similar to the sea fishing needle, the range is not clear, and a large amount of manpower and material resources are required to be consumed.
Disclosure of Invention
The application aims to provide a zombie car identification method based on an intelligent vehicle-mounted terminal.
The technical scheme adopted by the application is as follows:
the zombie car identification method based on the intelligent vehicle-mounted terminal comprises the following steps of:
step 1, video acquisition is carried out on passing roadside vehicles by utilizing a vehicle-mounted terminal of the vehicle to obtain driving data with vehicle information, and the driving data with the vehicle information is uploaded to a data center;
step 2, the data center utilizes the identification of the roadside vehicle to the driving data by using an image algorithm,
step 3, judging whether the speed of the roadside vehicle is 0 by combining the pictures before and after the video; if yes, executing the step 4; otherwise, executing the step 2;
step 4, the data center obtains the longitude and latitude of the roadside vehicle, and judges whether the stay frequency of the roadside vehicle at the same longitude and latitude is larger than a set number n (n is an integer not smaller than 1) and the time interval from the first discovery is larger than a set threshold t (for example, t is 10 days) based on a vehicle information inquiry database; if yes, executing the step 5; otherwise, updating the database information and executing the step 2;
step 5, detecting video monitoring data near the roadside vehicle by the data center to judge whether the body of the roadside vehicle contains dust or leaves; if yes, extracting the vehicle condition state data of the roadside vehicle from the driving data and executing the step 6; otherwise, executing the step 2;
step 6, judging whether the vehicle condition is a zombie vehicle or not based on the vehicle condition state of the roadside vehicle;
and 7, the data center uploads the corresponding video which is judged to be the zombie vehicle to a video monitoring platform and reports the video to related departments.
Further, the specific steps of the step 1 are as follows: and in the running process of the vehicle, collecting stationary vehicle data at the front side edge in a fixed time period T to obtain a running data sequence U, and transmitting the collected running data sequence to a data center through a mobile cellular communication technology.
Further, the stationary vehicle data includes a position L of the vehicle, a license plate m, a time t, and direction information d.
Further, the data center acquires the longitude and latitude of the roadside vehicle at the corresponding moment based on the driving track data of the uploading vehicle-mounted terminal.
Further, the specific steps of updating the database in step 4 are as follows:
step 4.1, searching a database for whether other vehicle information exists in the longitude and latitude; if yes, the vehicle information of the longitude and latitude is cleared, and step 2 is executed; otherwise, executing the step 4.2;
step 4.2, searching whether different longitude and latitude information exists in the license plate in a database; if yes, the vehicle information is cleared from the database and the step 2 is executed; otherwise, the longitude and latitude and the frequency of the vehicle information in the database are +1, the time of the first occurrence is recorded, and the step 2 is executed.
Further, the step of judging the zombie vehicle in the step 6 is as follows:
step 6.1, judging whether the vehicle body is damaged or the vehicle tires are shrunken through a deep learning technology; if yes, judging that the road side vehicle is a zombie vehicle and executing the step 7; otherwise, executing the step 6.2;
step 6.2, judging whether the vehicle body has large-area rust spots or the front glass covers dust leaves in a large area through a local learning vehicle image recognition method; if yes, judging that the road side vehicle is a zombie vehicle and executing the step 7; otherwise, executing the step 6.3;
step 6.3, further determining whether the vehicle body is a small-area rust spot or the front glass is covered with a small-area dust leaf; if yes, judging that the roadside vehicle is a suspected zombie vehicle and executing the step 7; otherwise, judging that the roadside vehicle is not a zombie vehicle and executing the step 2.
Further, when the rust spots exceed 10% of the surface of the vehicle body, the vehicle body is considered to be large-area rust spots; the dust leaves cover 10% of the front glass surface of the vehicle, and the front glass is considered to cover the dust leaves in a large area.
Further, in step 7, the data center uploads the video through the 4G or 5G network.
According to the technical scheme, the vehicle is identified from the video based on the image algorithm, the zombie vehicle is primarily judged by utilizing the longitude and latitude, the speed and the threshold value, the zombie vehicle is finally identified by the deep learning technology and the vehicle image identification algorithm of local learning, and the information of the zombie vehicle is reported to related departments by utilizing the blockchain technology, so that the problems can be timely processed. Thereby achieving the purpose of correspondingly improving the number of parking spaces and improving the appearance and environment of urban areas.
Drawings
The application is described in further detail below with reference to the drawings and detailed description;
fig. 1 is a flow chart of a zombie vehicle identification method based on an intelligent vehicle-mounted terminal.
Detailed Description
For the purpose of making the objects, technical solutions and advantages of the embodiments of the present application more apparent, the technical solutions of the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present application, and it is apparent that the described embodiments are some embodiments of the present application, but not all embodiments of the present application. The components of the embodiments of the present application generally described and illustrated in the figures herein may be arranged and designed in a wide variety of different configurations. Thus, the following detailed description of the embodiments of the application, as presented in the figures, is not intended to limit the scope of the application, as claimed, but is merely representative of selected embodiments of the application. All other embodiments, which can be made by those skilled in the art based on the embodiments of the application without making any inventive effort, are intended to be within the scope of the application.
As shown in fig. 1, the application discloses a zombie car identification method based on an intelligent vehicle-mounted terminal, which comprises the following steps:
step 1, video acquisition is carried out on passing roadside vehicles by utilizing a vehicle-mounted terminal of the vehicle to obtain driving data with vehicle information, and the driving data with the vehicle information is uploaded to a data center;
step 2, the data center utilizes the identification of the roadside vehicle to the driving data by using an image algorithm,
step 3, judging whether the speed of the roadside vehicle is 0 by combining the pictures before and after the video; if yes, executing the step 4; otherwise, executing the step 2;
step 4, the data center acquires the longitude and latitude of the roadside vehicle, and judges whether the stay frequency of the roadside vehicle at the same longitude and latitude is larger than a set number n and the time interval from first discovery is larger than a set threshold t based on a vehicle information inquiry database; if yes, executing the step 5; otherwise, updating the database information and executing the step 2;
step 5, detecting video monitoring data near the roadside vehicle by the data center to judge whether the body of the roadside vehicle contains dust or leaves; if yes, extracting the vehicle condition state data of the roadside vehicle from the driving data and executing the step 6; otherwise, executing the step 2;
step 6, judging whether the vehicle condition is a zombie vehicle or not based on the vehicle condition state of the roadside vehicle;
and 7, the data center uploads the corresponding video which is judged to be the zombie vehicle to a video monitoring platform and reports the video to related departments.
Further, the specific steps of the step 1 are as follows: and in the running process of the vehicle, collecting stationary vehicle data at the front side edge in a fixed time period T to obtain a running data sequence U, and transmitting the collected running data sequence to a data center through a mobile cellular communication technology.
Further, the stationary vehicle data includes a position L of the vehicle, a license plate m, a time t, and direction information d.
Further, the data center acquires the longitude and latitude of the roadside vehicle at the corresponding moment based on the driving track data of the uploading vehicle-mounted terminal.
Further, the specific steps of updating the database information and executing the step 2 in the step 4 are as follows:
step 4.1, searching a database for whether other vehicle information exists in the longitude and latitude; if yes, the vehicle information of the longitude and latitude is cleared, and step 2 is executed; otherwise, executing the step 4.2;
step 4.2, searching whether different longitude and latitude information exists in the license plate in a database; if yes, the vehicle information is cleared from the database and the step 2 is executed; otherwise, the longitude and latitude and the frequency of the vehicle information in the database are +1, the time of the first occurrence is recorded, and the step 2 is executed.
Further, the step of judging the zombie vehicle in the step 6 is as follows:
step 6.1, judging whether the vehicle body is damaged or the vehicle tires are shrunken through a deep learning technology; if yes, judging that the road side vehicle is a zombie vehicle and executing the step 7; otherwise, executing the step 6.2;
step 6.2, judging whether the vehicle body has large-area rust spots or the front glass covers dust leaves in a large area through a local learning vehicle image recognition method; if yes, judging that the road side vehicle is a zombie vehicle and executing the step 7; otherwise, executing the step 6.3;
step 6.3, further determining whether the vehicle body is a small-area rust spot or the front glass is covered with a small-area dust leaf; if yes, judging that the roadside vehicle is a suspected zombie vehicle and executing the step 7; otherwise, judging that the roadside vehicle is not a zombie vehicle and executing the step 2.
Further, when the rust spots exceed 10% of the surface of the vehicle body, the vehicle body is considered to be large-area rust spots; the dust leaves cover 10% of the front glass surface of the vehicle, and the front glass is considered to cover the dust leaves in a large area.
Further, in step 7, the data center uploads the video through the 4G or 5G network.
According to the technical scheme, the vehicle is identified from the video based on the image algorithm, the zombie vehicle is primarily judged by utilizing the longitude and latitude, the speed and the threshold value, the zombie vehicle is finally identified by the deep learning technology and the vehicle image identification algorithm of local learning, and the information of the zombie vehicle is reported to related departments by utilizing the blockchain technology, so that the problems can be timely processed. Thereby achieving the purpose of correspondingly improving the number of parking spaces and improving the appearance and environment of urban areas.
Claims (7)
1. The zombie car identification method based on the intelligent vehicle-mounted terminal is characterized by comprising the following steps of: which comprises the following steps:
step 1, video acquisition is carried out on passing roadside vehicles by utilizing a vehicle-mounted terminal of the vehicle to obtain driving data with vehicle information, and the driving data with the vehicle information is uploaded to a data center;
step 2, the data center identifies the roadside vehicle by using an image algorithm for the driving data,
step 3, judging whether the speed of the roadside vehicle is 0 by combining the pictures before and after the video; if yes, executing the step 4; otherwise, executing the step 2;
step 4, the data center acquires the longitude and latitude of the roadside vehicle, and judges whether the stay frequency of the roadside vehicle at the same longitude and latitude is larger than a set number n and the time interval from first discovery is larger than a set threshold t based on a vehicle information inquiry database; if yes, executing the step 5; otherwise, updating the database information and executing the step 2;
step 5, the data center detects video monitoring data near the roadside vehicle to judge whether the body of the roadside vehicle contains dust or leaves; if yes, extracting the vehicle condition state data of the roadside vehicle from the driving data and executing the step 6; otherwise, executing the step 2;
step 6, judging whether the vehicle is a zombie vehicle or not based on the condition state of the roadside vehicle; the step of judging the zombie vehicle in the step 6 is as follows:
step 6.1, judging whether the vehicle body is damaged or the vehicle tires are shrunken through a deep learning technology; if yes, judging that the road side vehicle is a zombie vehicle and executing the step 7; otherwise, executing the step 6.2;
step 6.2, judging whether the vehicle body has large-area rust spots or the front glass covers dust leaves in a large area through a vehicle image recognition method of local learning; if yes, judging that the road side vehicle is a zombie vehicle and executing the step 7; otherwise, executing the step 6.3;
step 6.3, further determining whether the vehicle body is a small-area rust spot or the front glass is covered with a small-area dust leaf; if yes, judging that the roadside vehicle is a suspected zombie vehicle and executing the step 7; otherwise, judging that the roadside vehicle is not a zombie vehicle and executing the step 2;
and 7, the data center uploads the corresponding video which is judged to be the zombie vehicle to a video monitoring platform and reports the video to related departments.
2. The zombie car identification method based on the intelligent vehicle-mounted terminal according to claim 1, wherein the zombie car identification method is characterized in that: the specific steps of the step 1 are as follows: and in the running process of the vehicle, collecting stationary vehicle data at the front side edge in a fixed time period T to obtain a running data sequence U, and transmitting the collected running data sequence to a data center through a mobile cellular communication technology.
3. The zombie car identification method based on the intelligent vehicle-mounted terminal according to claim 2, wherein the zombie car identification method is characterized in that: the stationary vehicle data includes the position L of the vehicle, the license plate m, the time t, and the direction information d.
4. The zombie car identification method based on the intelligent vehicle-mounted terminal according to claim 1, wherein the zombie car identification method is characterized in that: the data center obtains the longitude and latitude of the roadside vehicle at the corresponding moment based on the driving track data of the uploading vehicle-mounted terminal.
5. The zombie car identification method based on the intelligent vehicle-mounted terminal according to claim 1, wherein the zombie car identification method is characterized in that: the specific steps for updating the database in the step 4 are as follows:
step 4.1, searching a database for whether other vehicle information exists in the longitude and latitude; if yes, the vehicle information of the longitude and latitude is cleared, and step 2 is executed; otherwise, executing the step 4.2;
step 4.2, searching whether different longitude and latitude information exists in license plates corresponding to the roadside vehicles in a database; if yes, the vehicle information is cleared from the database and the step 2 is executed; otherwise, the longitude and latitude and the frequency of the vehicle information in the database are +1, the time of the first occurrence is recorded, and the step 2 is executed.
6. The zombie car identification method based on the intelligent vehicle-mounted terminal according to claim 1, wherein the zombie car identification method is characterized in that: when the rust spots exceed 10% of the surface of the vehicle body, the large-area rust spots of the vehicle body are considered; the dust leaves cover 10% of the front glass surface of the vehicle, and the front glass is considered to cover the dust leaves in a large area.
7. The zombie car identification method based on the intelligent vehicle-mounted terminal according to claim 1, wherein the zombie car identification method is characterized in that: and step 7, uploading the video by the data center through a 4G or 5G network.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010253041.7A CN111461024B (en) | 2020-04-02 | 2020-04-02 | Zombie vehicle identification method based on intelligent vehicle-mounted terminal |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010253041.7A CN111461024B (en) | 2020-04-02 | 2020-04-02 | Zombie vehicle identification method based on intelligent vehicle-mounted terminal |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111461024A CN111461024A (en) | 2020-07-28 |
| CN111461024B true CN111461024B (en) | 2023-08-25 |
Family
ID=71681176
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010253041.7A Active CN111461024B (en) | 2020-04-02 | 2020-04-02 | Zombie vehicle identification method based on intelligent vehicle-mounted terminal |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111461024B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116416795B (en) * | 2023-04-06 | 2023-11-10 | 广东云钜网络科技有限公司 | Zombie car monitoring method and system based on traffic big data |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2014003167A1 (en) * | 2012-06-29 | 2014-01-03 | 株式会社デンソー | Vehicle-mounted image analysis device |
| CN107945566A (en) * | 2017-11-17 | 2018-04-20 | 张慧 | Curb parking management system and method based on multiple target tracking and deep learning |
| CN110490984A (en) * | 2019-07-12 | 2019-11-22 | 智慧互通科技有限公司 | A kind of Roadside Parking management system and method |
| CN110517503A (en) * | 2019-08-28 | 2019-11-29 | 武汉烽火众智数字技术有限责任公司 | Corpse vehicle analysis and early warning method and device based on big data |
-
2020
- 2020-04-02 CN CN202010253041.7A patent/CN111461024B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2014003167A1 (en) * | 2012-06-29 | 2014-01-03 | 株式会社デンソー | Vehicle-mounted image analysis device |
| CN107945566A (en) * | 2017-11-17 | 2018-04-20 | 张慧 | Curb parking management system and method based on multiple target tracking and deep learning |
| CN110490984A (en) * | 2019-07-12 | 2019-11-22 | 智慧互通科技有限公司 | A kind of Roadside Parking management system and method |
| CN110517503A (en) * | 2019-08-28 | 2019-11-29 | 武汉烽火众智数字技术有限责任公司 | Corpse vehicle analysis and early warning method and device based on big data |
Non-Patent Citations (1)
| Title |
|---|
| 视觉注意模型的道路监控视频关键帧提取;刘云鹏，张三元;《中国图像图形学报》;全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111461024A (en) | 2020-07-28 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108074396A (en) | The evaluation method that drives safely and system | |
| CN108848460B (en) | Man-vehicle association method based on RFID and GPS data | |
| CN101799977A (en) | Intelligent traffic system | |
| CN103050013B (en) | Based on vehicle classification speed limit method for supervising and the device thereof of car networking technology | |
| US11640560B2 (en) | Automated training data quality process | |
| CN109166319A (en) | A kind of highway illegal activities recognition methods based on block chain technology | |
| CN104766479A (en) | Automobile identity recognition method and device based on ultrahigh frequency radio frequency and video image dual-recognition matching | |
| CN109345853A (en) | A kind of unmanned vehicle safe driving optimization method based on GIS | |
| CN111461024B (en) | Zombie vehicle identification method based on intelligent vehicle-mounted terminal | |
| CN103390145A (en) | Target region vehicle detection method and system | |
| CN114387785A (en) | Safety management and control method and system based on intelligent highway and storable medium | |
| CN111866834A (en) | Storage battery car violation information identification and monitoring system and method based on RFID data | |
| US10930145B2 (en) | Traffic system for predicting and providing traffic signal switching timing | |
| CN115099267A (en) | Pavement evenness maintenance method, system, detection terminal and server | |
| CN108665712A (en) | A kind of vehicle gets over line act of violating regulations monitoring method and system | |
| CN110335370A (en) | A kind of urgent lane keeps update method, device and the automobile of miscellaneous function | |
| CN116092037B (en) | Vehicle type identification method integrating track space-semantic features | |
| CN114898309A (en) | City intelligent inspection vehicle system and inspection method based on visual AI technology | |
| Walcott-Bryant et al. | Harsh brakes at potholes in Nairobi: Context-based driver behavior in developing cities | |
| CN114339766B (en) | Urban Internet of vehicles Sybil attack detection method based on coarse-fine granularity tracks | |
| CN109887309A (en) | A kind of vehicle on highway speed monitoring system and monitoring method | |
| CN115757628A (en) | Vehicle collision detection method, device, equipment and medium | |
| CN116412854A (en) | Road surface information data acquisition system based on 5G car networking | |
| CN110544378B (en) | Method for judging traffic jam condition of mobile phone user | |
| CN117542188A (en) | Method and device for precisely pushing vehicle service information and terminal equipment |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |