CN111986473A - Big data processing method based on vehicle type identification - Google Patents
Big data processing method based on vehicle type identification Download PDFInfo
- Publication number
- CN111986473A CN111986473A CN201910436964.3A CN201910436964A CN111986473A CN 111986473 A CN111986473 A CN 111986473A CN 201910436964 A CN201910436964 A CN 201910436964A CN 111986473 A CN111986473 A CN 111986473A
- Authority
- CN
- China
- Prior art keywords
- image
- vehicle
- sub
- equipment
- linear interpolation
- 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- Withdrawn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
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/01—Detecting movement of traffic to be counted or controlled
- G08G1/0104—Measuring and analyzing of parameters relative to traffic conditions
- G08G1/0125—Traffic data processing
- G08G1/0129—Traffic data processing for creating historical data or processing based on historical data
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/50—Context or environment of the image
- G06V20/52—Surveillance or monitoring of activities, e.g. for recognising suspicious objects
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/01—Detecting movement of traffic to be counted or controlled
- G08G1/015—Detecting movement of traffic to be counted or controlled with provision for distinguishing between two or more types of vehicles, e.g. between motor-cars and cycles
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/09—Arrangements for giving variable traffic instructions
-
- 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
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Chemical & Material Sciences (AREA)
- Analytical Chemistry (AREA)
- Traffic Control Systems (AREA)
- Image Processing (AREA)
Abstract
The invention relates to a big data processing method based on vehicle type identification, which comprises the steps of using a big data processing system based on vehicle type identification to estimate and wait for each vehicle which is arranged in the front and can pass through at the next green light in vehicles based on historical data, and carrying out field projection on each vehicle.
Description
Technical Field
The invention relates to the field of big data processing, in particular to a big data processing method based on vehicle type identification.
Background
The big data processing complies with the flow of capturing, storing and analyzing, and data in the process are acquired by a sensor, a webpage server, a sales terminal, mobile equipment and the like, then are stored in corresponding equipment, and then are analyzed. Since these types of processing are performed by conventional relational database management systems, the data format needs to be converted or translated into the type of structure that the RDBMS can use, such as in rows or columns, and needs to be contiguous with other data.
The process of processing is referred to as extracting, transferring, loading, or as ETL. Firstly, data is extracted from a source system and processed, then the data is standardized and sent to a corresponding data warehouse for further analysis. In a traditional database environment, such ETL steps are relatively straightforward, as the objects of analysis are often well-known financial reports, sales or marketing reports, enterprise resource planning, and so forth. In a big data environment, however, ETL may become relatively complex, and thus the transformation process is different for the way it is handled between different types of data sources. When the analysis begins, the data is first pulled from the data warehouse and placed into the RDBMS to generate the required reports or support the corresponding business intelligence applications. In the context of big data analysis, the bare data and the transformed data are mostly saved, since it may be necessary to transform them again later.
Disclosure of Invention
The invention needs to have the following two key points:
(1) estimating each vehicle which can pass through and is arranged in the front row in the next green light release of the equal-light vehicles based on historical data, and carrying out on-site projection on each vehicle, thereby reducing the anxiety degree of the equal-light driver;
(2) and respectively executing interpolation processing mechanisms with different strategies on a target area and a non-target area in the image, thereby ensuring the reliability of subsequent image identification action on the basis of avoiding executing too complex multiple interpolation processing on the whole image.
According to an aspect of the present invention, there is provided a big data processing method based on vehicle type identification, the method including using a big data processing system based on vehicle type identification to estimate, based on historical data, and the like, respective vehicles in front of which green lights are next allowed to pass through, and projecting the respective vehicles on site, the big data processing system based on vehicle type identification including: the big data processing node is connected with the wiener filtering equipment through a network and used for identifying the vehicle type corresponding to each vehicle target in the field filtering image based on the imaging characteristics of various vehicles; the big data processing node also determines the average time of the vehicle type vehicle passing through the traffic intersection according to the vehicle type corresponding to each vehicle target, and the average time is obtained based on historical data statistics; the big data processing node also determines a plurality of vehicle targets with the lightest depth of field in the field filtering image which can pass through the traffic intersection within the duration of the next green light according to the duration of the green light in the signal lamp and each average time corresponding to each vehicle target in the field filtering image; the field projection equipment is arranged on a cross bar where a signal lamp above a traffic intersection is located, is connected with the big data processing node through a network, and is used for determining the area commonly occupied by a plurality of vehicle targets in an actual scene based on the positions of the vehicle targets with the shallowest depth of field in the field filtering image respectively and performing field projection operation on the commonly occupied area; in the big data processing node, the sum of a plurality of average times respectively corresponding to a plurality of vehicle types of a plurality of vehicle targets with the shallowest depth of field in the field filtering image is close to or equal to the duration of the green light.
The big data processing method based on vehicle type identification has rapid operation and certain intelligent level. The method has the advantages that the method estimates that each vehicle in the front row which can pass through is released by the next green light in the equal-light vehicles based on historical data, and performs on-site projection on each vehicle, so that the anxiety degree of the equal-light driver is reduced.
Drawings
Embodiments of the invention will now be described with reference to the accompanying drawings, in which:
fig. 1 is a schematic view of a traffic intersection where a big data processing system based on vehicle type identification is located according to an embodiment of the present invention.
Detailed Description
Embodiments of the present invention will be described in detail below with reference to the accompanying drawings.
Traffic control, also called traffic signal control, or urban traffic control, is to direct the traffic of vehicles and pedestrians by means of traffic police or by means of traffic signal control facilities according to the traffic change characteristics.
The traffic control uses modern communication facilities, signal devices, sensors, monitoring equipment and computers to accurately organize and regulate running vehicles, so that the vehicles can run safely and smoothly. Traffic control is classified into static management and dynamic management, and traffic control is dynamic management thereof.
The traffic control system limits, regulates, induces and shunts the traffic flow through the traffic control facilities managed by the electronic computer so as to achieve the purposes of reducing the total traffic volume, dredging the traffic and ensuring the traffic safety and smoothness.
At present, for drivers of vehicles waiting in line at a traffic intersection, the mood during the red light forbidden time period is anxious, whether the vehicle can pass through the traffic intersection in the next green light release time period cannot be determined, and therefore the vehicle is in a standby state at that time, so that the key of the problem is that the vehicles in the front row of the next green light release time cannot be accurately determined.
In order to overcome the defects, the invention builds a big data processing method based on vehicle type identification, and the method comprises the steps of using a big data processing system based on vehicle type identification to enable each vehicle which is arranged in the front and can pass through to be released by a green light at the next time in light vehicles based on historical data estimation and the like, and carrying out field projection on each vehicle. The big data processing system based on vehicle type identification can effectively solve corresponding technical problems.
Fig. 1 is a schematic view of a traffic intersection where a big data processing system based on vehicle type identification is located according to an embodiment of the present invention.
The big data processing system based on vehicle type identification according to the embodiment of the invention comprises:
the big data processing node is connected with the wiener filtering equipment through a network and used for identifying the vehicle type corresponding to each vehicle target in the field filtering image based on the imaging characteristics of various vehicles;
the big data processing node also determines the average time of the vehicle type vehicle passing through the traffic intersection according to the vehicle type corresponding to each vehicle target, and the average time is obtained based on historical data statistics;
the big data processing node also determines a plurality of vehicle targets with the lightest depth of field in the field filtering image which can pass through the traffic intersection within the duration of the next green light according to the duration of the green light in the signal lamp and each average time corresponding to each vehicle target in the field filtering image;
the field projection equipment is arranged on a cross bar where a signal lamp above a traffic intersection is located, is connected with the big data processing node through a network, and is used for determining the area commonly occupied by a plurality of vehicle targets in an actual scene based on the positions of the vehicle targets with the shallowest depth of field in the field filtering image respectively and performing field projection operation on the commonly occupied area;
In the big data processing node, the sum of a plurality of average times respectively corresponding to a plurality of vehicle types of a plurality of vehicle targets with the shallowest depth of field in the field filtering image is close to or equal to the duration of the green light;
the high-definition snapshot device is arranged on a cross bar where a signal lamp above a traffic intersection is located, is located on one side of the signal lamp, and is used for carrying out snapshot operation on vehicle queuing scenes of the lights in front of the traffic intersection to obtain a light waiting scene image;
the contrast improving equipment is arranged in the control box below the cross rod, is connected with the high-definition capturing equipment, and is used for performing contrast improving processing on the received isolightlike scene images to obtain corresponding real-time improved images and outputting the real-time improved images;
the signal searching device is connected with the contrast improving device and used for receiving the real-time improving image, searching out a corresponding vehicle sub-image from the real-time improving image based on the vehicle image characteristic, and taking the image except the vehicle sub-image in the real-time improving image as a residual sub-image;
the linear interpolation device is connected with the signal searching device and used for performing linear interpolation processing on the vehicle sub-image to obtain a first sub-image;
The linear interpolation device is further used for performing linear interpolation processing on the residual sub-image to obtain a second sub-image;
the moving average interpolation device is respectively connected with the signal searching device and the linear interpolation device and is used for receiving the first sub-image;
the moving average interpolation device is further configured to perform moving average interpolation processing on the first sub-image to obtain a third sub-image;
the data combination equipment is respectively connected with the linear interpolation equipment and the moving average interpolation equipment and is used for respectively carrying out normalization processing operation on the second sub-image and the third sub-image so as to respectively obtain a fourth sub-image and a fifth sub-image;
the data combination device is further configured to merge the fourth sub-image and the fifth sub-image to obtain a merged image;
and the wiener filtering equipment is connected with the data combination equipment and is used for receiving the combined image and executing wiener filtering processing on the combined image so as to obtain and output a corresponding field filtering image.
Next, the detailed configuration of the big data processing system based on vehicle type identification according to the present invention will be further described.
In the big data processing system based on vehicle type identification:
and the linear interpolation equipment is also used for directly sending the vehicle sub-image as the first sub-image to the moving average interpolation equipment when the definition of the vehicle sub-image is detected to be out of limit.
In the big data processing system based on vehicle type identification:
and the linear interpolation equipment is also used for directly sending the residual sub-image as a second sub-image to the moving average interpolation equipment when the definition of the residual sub-image is detected to be out of limit.
In the big data processing system based on vehicle type identification:
the wiener filtering device, the linear interpolation device and the moving average interpolation device are respectively realized by SOC chips with different models.
The big data processing system based on vehicle type identification can further comprise:
and the FPM DRAM is respectively connected with the linear interpolation device and the moving average interpolation device and is used for respectively storing the current input data of the linear interpolation device and the moving average interpolation device.
The big data processing system based on vehicle type identification can further comprise:
and the frequency division duplex communication interface is connected with the linear interpolation equipment and is used for transmitting the current transmission data of the linear interpolation equipment through a frequency division duplex communication link.
In the big data processing system based on vehicle type identification:
the linear interpolation device and the moving average interpolation device are respectively realized by SOC chips with different models and are integrated on the same printed circuit board.
The big data processing system based on vehicle type identification can further comprise:
and the temperature sensing equipment is respectively connected with the linear interpolation equipment and the moving average interpolation equipment and is used for respectively detecting the shell temperatures of the linear interpolation equipment and the moving average interpolation equipment.
In addition, FPM DRAM (Fast Page Mode RAM): fast page mode memory. Is a memory that was commonly used during time 486 (also used as video memory). 72 lines, 5V voltage, 32bit bandwidth and basic speed of more than 60 ns. Its read cycle begins with the triggering of a row in the DRAM array and then moves to the location pointed by the memory address, i.e., contains the desired data. The first message must be validated and stored to the system in preparation for the next cycle. This introduces a "wait state" because the CPU must wait for the memory to complete one cycle foolproof. One important reason for the widespread use of FPM is that it is a standard and safe product and is inexpensive. But its performance deficiency has led to its replacement by EDO DRAM soon, and such video-backed video cards are not yet available.
Those of ordinary skill in the art will understand that: all or part of the steps for implementing the method embodiments may be implemented by hardware related to program instructions, and the program may be stored in a computer readable storage medium, and when executed, the program performs the steps including the method embodiments; and the aforementioned storage medium includes: Read-Only Memory (ROM), Random Access Memory (RAM), magnetic or optical disk, and other various media capable of storing program codes.
Finally, it should be noted that: the above embodiments are only used to illustrate the technical solution of the present invention, and not to limit the same; while the invention has been described in detail and with reference to the foregoing embodiments, it will be understood by those skilled in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some or all of the technical features may be equivalently replaced; and the modifications or the substitutions do not make the essence of the corresponding technical solutions depart from the scope of the technical solutions of the embodiments of the present invention.
Claims (8)
1. A vehicle type identification-based big data processing method, the method comprising using a vehicle type identification-based big data processing system to estimate, based on historical data, that each vehicle in the front row that can pass is released by the next green light among lights-waiting vehicles, and to project the vehicle on site, the vehicle type identification-based big data processing system comprising:
The big data processing node is connected with the wiener filtering equipment through a network and used for identifying the vehicle type corresponding to each vehicle target in the field filtering image based on the imaging characteristics of various vehicles;
the big data processing node also determines the average time of the vehicle type vehicle passing through the traffic intersection according to the vehicle type corresponding to each vehicle target, and the average time is obtained based on historical data statistics;
the big data processing node also determines a plurality of vehicle targets with the lightest depth of field in the field filtering image which can pass through the traffic intersection within the duration of the next green light according to the duration of the green light in the signal lamp and each average time corresponding to each vehicle target in the field filtering image;
the field projection equipment is arranged on a cross bar where a signal lamp above a traffic intersection is located, is connected with the big data processing node through a network, and is used for determining the area commonly occupied by a plurality of vehicle targets in an actual scene based on the positions of the vehicle targets with the shallowest depth of field in the field filtering image respectively and performing field projection operation on the commonly occupied area;
in the big data processing node, the sum of a plurality of average times respectively corresponding to a plurality of vehicle types of a plurality of vehicle targets with the shallowest depth of field in the field filtering image is close to or equal to the duration of the green light;
The high-definition snapshot device is arranged on a cross bar where a signal lamp above a traffic intersection is located, is located on one side of the signal lamp, and is used for carrying out snapshot operation on vehicle queuing scenes of the lights in front of the traffic intersection to obtain a light waiting scene image;
the contrast improving equipment is arranged in the control box below the cross rod, is connected with the high-definition capturing equipment, and is used for performing contrast improving processing on the received isolightlike scene images to obtain corresponding real-time improved images and outputting the real-time improved images;
the signal searching device is connected with the contrast improving device and used for receiving the real-time improving image, searching out a corresponding vehicle sub-image from the real-time improving image based on the vehicle image characteristic, and taking the image except the vehicle sub-image in the real-time improving image as a residual sub-image;
the linear interpolation device is connected with the signal searching device and used for performing linear interpolation processing on the vehicle sub-image to obtain a first sub-image;
the linear interpolation device is further used for performing linear interpolation processing on the residual sub-image to obtain a second sub-image;
the moving average interpolation device is respectively connected with the signal searching device and the linear interpolation device and is used for receiving the first sub-image;
The moving average interpolation device is further configured to perform moving average interpolation processing on the first sub-image to obtain a third sub-image;
the data combination equipment is respectively connected with the linear interpolation equipment and the moving average interpolation equipment and is used for respectively carrying out normalization processing operation on the second sub-image and the third sub-image so as to respectively obtain a fourth sub-image and a fifth sub-image;
the data combination device is further configured to merge the fourth sub-image and the fifth sub-image to obtain a merged image;
and the wiener filtering equipment is connected with the data combination equipment and is used for receiving the combined image and executing wiener filtering processing on the combined image so as to obtain and output a corresponding field filtering image.
2. The method of claim 1, wherein:
and the linear interpolation equipment is also used for directly sending the vehicle sub-image as the first sub-image to the moving average interpolation equipment when the definition of the vehicle sub-image is detected to be out of limit.
3. The method of claim 2, wherein:
and the linear interpolation equipment is also used for directly sending the residual sub-image as a second sub-image to the moving average interpolation equipment when the definition of the residual sub-image is detected to be out of limit.
4. The method of claim 3, wherein:
the wiener filtering device, the linear interpolation device and the moving average interpolation device are respectively realized by SOC chips with different models.
5. The method of claim 4, wherein the system further comprises:
and the FPM DRAM is respectively connected with the linear interpolation device and the moving average interpolation device and is used for respectively storing the current input data of the linear interpolation device and the moving average interpolation device.
6. The method of claim 5, wherein the system further comprises:
and the frequency division duplex communication interface is connected with the linear interpolation equipment and is used for transmitting the current transmission data of the linear interpolation equipment through a frequency division duplex communication link.
7. The method of claim 6, wherein:
the linear interpolation device and the moving average interpolation device are respectively realized by SOC chips with different models and are integrated on the same printed circuit board.
8. The method of claim 7, wherein the system further comprises:
And the temperature sensing equipment is respectively connected with the linear interpolation equipment and the moving average interpolation equipment and is used for respectively detecting the shell temperatures of the linear interpolation equipment and the moving average interpolation equipment.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910436964.3A CN111986473A (en) | 2019-05-24 | 2019-05-24 | Big data processing method based on vehicle type identification |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910436964.3A CN111986473A (en) | 2019-05-24 | 2019-05-24 | Big data processing method based on vehicle type identification |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111986473A true CN111986473A (en) | 2020-11-24 |
Family
ID=73436836
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910436964.3A Withdrawn CN111986473A (en) | 2019-05-24 | 2019-05-24 | Big data processing method based on vehicle type identification |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111986473A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113593274A (en) * | 2021-07-29 | 2021-11-02 | 青岛海信网络科技股份有限公司 | Traffic signal control method and device |
| CN113851000A (en) * | 2021-09-10 | 2021-12-28 | 泰州蝶金软件有限公司 | Command analysis system based on cloud computing |
-
2019
- 2019-05-24 CN CN201910436964.3A patent/CN111986473A/en not_active Withdrawn
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113593274A (en) * | 2021-07-29 | 2021-11-02 | 青岛海信网络科技股份有限公司 | Traffic signal control method and device |
| CN113851000A (en) * | 2021-09-10 | 2021-12-28 | 泰州蝶金软件有限公司 | Command analysis system based on cloud computing |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| EP3806064B1 (en) | Method and apparatus for detecting parking space usage condition, electronic device, and storage medium | |
| US8837906B2 (en) | Computer assisted dispatch incident report video search and tagging systems and methods | |
| CN110390813B (en) | Big data processing system based on vehicle type identification | |
| US11508163B2 (en) | Method and apparatus for training lane line identifying model, device, and storage medium | |
| EP3955218A2 (en) | Lane line detection method and apparatus, electronic device, computer storage medium, and computer program product | |
| CN109284801B (en) | Traffic indicator lamp state identification method and device, electronic equipment and storage medium | |
| CN111986473A (en) | Big data processing method based on vehicle type identification | |
| Salma et al. | Smart parking guidance system using 360o camera and haar-cascade classifier on iot system | |
| Hosseini et al. | An unsupervised learning framework for detecting adaptive cruise control operated vehicles in a vehicle trajectory data | |
| JP7429756B2 (en) | Image processing method, device, electronic device, storage medium and computer program | |
| CN112235262A (en) | Message analysis method and device, electronic equipment and computer readable storage medium | |
| CN111507269B (en) | Parking space state identification method and device, storage medium and electronic device | |
| CN112654999B (en) | Method and device for determining labeling information | |
| US20170133059A1 (en) | Method and system for video data stream storage | |
| US20240221426A1 (en) | Behavior detection method, electronic device, and computer readable storage medium | |
| CN115601738B (en) | Parking information acquisition method, device, equipment, storage medium and program product | |
| CN114550129B (en) | Machine learning model processing method and system based on data set | |
| CN115061386B (en) | Intelligent driving automatic simulation test system and related equipment | |
| CN112949359A (en) | Convolutional neural network-based abnormal behavior identification method and device | |
| CN113408514B (en) | Method and device for detecting berths of roadside parking lot based on deep learning | |
| CN112437274B (en) | Transmission method of snapshot picture and snapshot machine | |
| WO2021218384A1 (en) | Algorithm update method, system and device | |
| KAMAROZAMAN et al. | ENHANCING CAMPUS SECURITY AND VEHICLE MANAGEMENT WITH REAL-TIME MOBILE LICENSE PLATE READER APP UTILIZING A LIGHTWEIGHT INTEGRATION MODEL | |
| US20150120693A1 (en) | Image search system and image search method | |
| CN112966606B (en) | Image recognition method, related device and computer program product |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| WW01 | Invention patent application withdrawn after publication | ||
| WW01 | Invention patent application withdrawn after publication |
Application publication date: 20201124 |