CN113345224B - Highway data high efficiency storage system based on computer vision - Google Patents
Highway data high efficiency storage system based on computer vision Download PDFInfo
- Publication number
- CN113345224B CN113345224B CN202110561075.7A CN202110561075A CN113345224B CN 113345224 B CN113345224 B CN 113345224B CN 202110561075 A CN202110561075 A CN 202110561075A CN 113345224 B CN113345224 B CN 113345224B
- Authority
- CN
- China
- Prior art keywords
- data
- correlation
- road section
- lane
- score
- 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
- 230000008447 perception Effects 0.000 claims abstract description 19
- 238000000034 method Methods 0.000 claims description 23
- 239000011159 matrix material Substances 0.000 claims description 22
- 238000013500 data storage Methods 0.000 claims description 13
- 238000012935 Averaging Methods 0.000 claims description 9
- 238000004364 calculation method Methods 0.000 claims description 8
- 238000005452 bending Methods 0.000 claims description 6
- 230000008030 elimination Effects 0.000 claims description 4
- 238000003379 elimination reaction Methods 0.000 claims description 4
- 238000004458 analytical method Methods 0.000 claims description 3
- 238000010219 correlation analysis Methods 0.000 claims description 3
- 238000012545 processing Methods 0.000 abstract description 2
- 230000003247 decreasing effect Effects 0.000 description 4
- 238000010586 diagram Methods 0.000 description 3
- 230000000694 effects Effects 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000013135 deep learning Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000007726 management method Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 238000005192 partition Methods 0.000 description 1
- 230000035515 penetration Effects 0.000 description 1
- 230000002688 persistence Effects 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
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
-
- 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
- G08G1/052—Detecting movement of traffic to be counted or controlled with provision for determining speed or overspeed
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/065—Traffic control systems for road vehicles by counting the vehicles in a section of the road or in a parking area, i.e. comparing incoming count with outgoing count
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/50—Network services
- H04L67/56—Provisioning of proxy services
- H04L67/568—Storing data temporarily at an intermediate stage, e.g. caching
- H04L67/5682—Policies or rules for updating, deleting or replacing the stored data
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Chemical & Material Sciences (AREA)
- Analytical Chemistry (AREA)
- Engineering & Computer Science (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Traffic Control Systems (AREA)
Abstract
The invention relates to the technical field of computer vision, in particular to a highway data efficient storage system based on computer vision. The system comprises a data acquisition module, a risk data acquisition module and a data processing module, wherein the data acquisition module is used for acquiring perception data and risk data; the trend correlation acquisition module is used for acquiring the trend correlation between the lane speed and the lane flow; a road section priority value obtaining module 30, configured to obtain a correlation between the sensing data and the risk data, and obtain a road section priority value by combining the trend correlation and the road curvature degree; the road section score acquisition module is used for acquiring each road section score according to the long-range correlation of the historical sensing data, the road section priority value, the road section data access frequency and the time; the data caching module is used for caching data according to the score of each road section, and preferentially releasing the data with the lowest score of the road sections when the caching space is insufficient, so that the technical problems that in the prior art, the reading efficiency of important data in the high-speed highway data is low, and the data hit rate in the caching space is low are solved.
Description
Technical Field
The invention relates to the technical field of computer vision, in particular to a highway data efficient storage system based on computer vision.
Background
With the advancement of science and technology, highway data is increased in the data volume of a PB level, and how to realize higher-speed and more efficient storage of highway data under a large amount of data is an urgent problem.
The existing system and the information structure of the existing highway have some defects in the aspect of data storage, the existing highway data storage mostly adopts a general storage structure, and the characteristics of the highway data cannot be analyzed, so that the reading efficiency of important data in the highway data is low, and the data hit rate in a cache space is low.
Disclosure of Invention
In order to solve the above technical problems, the present invention aims to provide a computer vision-based highway data efficient storage system, which adopts the following technical scheme:
the embodiment of the invention provides a high-efficiency storage system of highway data based on computer vision, which comprises:
the data acquisition module is used for acquiring perception data and risk data in a preset time period on each road section; the perception data comprises lane flow, lane speed and overtaking times; the risk data comprises violation times and accident times;
the trend correlation acquisition module is used for respectively acquiring a first correlation of lane flow and a second correlation of lane speed between lanes in a period by adopting a correlation coefficient method and acquiring a trend correlation according to the first correlation and the second correlation;
the road section priority value acquisition module is used for obtaining a road section priority value according to the correlation between the perception data and the risk data in a period, the trend correlation and the road bending degree of each road section;
the road section score acquisition module is used for acquiring the long-range correlation of historical sensing data and acquiring the score of each road section by combining the road section priority value, the road section data access frequency and the time;
and the data caching module is used for caching data according to the score of each road section, and preferentially releasing the data with the lowest score of the road section when the caching space is insufficient.
Furthermore, the high-efficiency highway data storage system also comprises a data storage module, which is used for storing the data released by the data cache module; and in the released data, the data with high road section scores are stored at the outer circle of the disk, and the data with low road section scores are stored at the inner circle of the disk.
Further, the data acquisition module comprises:
the lane flow acquiring unit is used for acquiring the lane flow by adopting a target tracking method;
the lane speed acquisition unit is used for averaging the speeds of a plurality of vehicles measured at one position on each lane in the preset time period to obtain an average vehicle speed, and then averaging the average vehicle speeds obtained at intervals in the extension direction of each road section to obtain the lane speed;
and the overtaking number acquiring unit is used for acquiring the overtaking number according to the vehicle sequence acquired at intervals in the extending direction of each road section.
Further, the trend correlation acquisition module includes:
the first correlation obtaining unit is used for obtaining a first correlation matrix of the lane flow in a period by adopting a correlation coefficient method, and averaging the correlation between each lane flow in the first correlation matrix to obtain the first correlation;
and the second correlation obtaining unit is used for obtaining a second correlation matrix of the lane speeds in one period by adopting the correlation coefficient method, and averaging the correlation between each lane speed in the second correlation matrix to obtain the second correlation.
Further, the road section priority value acquisition module includes:
a correlation obtaining unit, configured to obtain a correlation between the perception data and the risk data by using a canonical correlation analysis method;
and the road bending degree acquisition unit is used for obtaining the road bending degree according to the ratio of the linear distance between the two end points of each road section to the total route.
Further, the link priority value is a product of the sum of the trend correlation and the degree of road curvature.
Further, the road section score acquisition module comprises a long-range correlation acquisition unit, and is used for respectively acquiring Hurst indexes reflecting the long-range correlations of the lane flow, the lane speed and the overtaking times from historical perception data by adopting a trend elimination fluctuation analysis method.
The embodiment of the invention at least has the following beneficial effects:
1. the embodiment of the invention obtains the trend correlation through the lane speed and the lane flow; obtaining correlation through perception data and risk data; obtaining a road section priority value through the trend correlation, the correlation and the road curvature degree; obtaining each road section score through long-range correlation of historical sensing data, road section priority values, road section data access frequency and time; the data caching is carried out according to the grade of each road section, when the caching space is insufficient, the data with the lowest grade of the road section is released preferentially, and the technical problems that in the prior art, the reading efficiency of important data in the high-speed road data is low, and the data hit rate in the caching space is low are solved.
2. The embodiment of the invention obtains the trend correlation through the lane speed and the lane flow; obtaining a correlation through the perception data and the risk data; and obtaining a road section priority value through the trend correlation, the correlation and the road curvature degree, wherein the road section priority value can better reflect the importance degree of data on the corresponding road section.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions and advantages of the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to the drawings without creative efforts;
FIG. 1 is a block diagram of a high-efficiency storage system for highway data based on computer vision according to an embodiment of the present invention;
fig. 2 is a block diagram of a system for efficiently storing highway data according to another embodiment of the present invention.
Detailed Description
To further illustrate the technical means and effects of the present invention for achieving the predetermined objects, the following detailed description of the embodiments, structures, features and effects of the present invention will be made with reference to the accompanying drawings and preferred embodiments. In the following description, different "one embodiment" or "another embodiment" refers to not necessarily the same embodiment. Furthermore, the particular features, structures, or characteristics may be combined in any suitable manner in one or more embodiments.
Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs.
The following describes a specific scheme of the highway data high-efficiency storage system based on computer vision in detail with reference to the accompanying drawings.
Referring to fig. 1, a block diagram of a high-efficiency highway data storage system based on computer vision according to an embodiment of the present invention is shown, where the high-efficiency highway data storage system 100 includes:
the data acquisition module 10 is used for acquiring perception data and risk data in a preset time period on each road section; the perception data comprises lane flow, lane speed and overtaking times; the risk data comprises the times of violation and the times of accidents.
The trend correlation obtaining module 20 is configured to obtain a first correlation of lane flow and a second correlation of lane speed between lanes in a cycle by using a correlation coefficient method, and obtain a trend correlation according to the first correlation and the second correlation.
And a road section priority value obtaining module 30, configured to obtain a road section priority value according to a correlation between the sensing data and the risk data in one cycle, a trend correlation, and a road curvature degree of each road section.
And the road section score acquisition module 40 is used for acquiring the long-range correlation of the historical sensing data and acquiring the score of each road section by combining the road section priority value, the road section data access frequency and the time.
And the data caching module 50 is configured to perform data caching according to each road segment score, and preferentially release data with the lowest road segment score when the caching space is insufficient.
In summary, the embodiment provides a high-efficiency highway data storage system based on computer vision, which obtains perception data and risk data through a data obtaining module 10; acquiring a trend correlation between the lane speed and the lane flow rate by a trend correlation acquisition module 20; obtaining the correlation between the perception data and the risk data through a road section priority value obtaining module 30, and obtaining a road section priority value by combining the trend correlation and the road curvature degree; the road section score obtaining module 40 obtains each road section score according to the long-range correlation of the historical sensing data, the road section priority value, the road section data access frequency and the time; the data caching module 50 caches data according to the score of each road section, and preferentially releases the data with the lowest score of the road sections when the caching space is insufficient, so that the technical problems that the reading efficiency of important data in high-speed highway data is low and the hit rate of the data in the caching space is low in the prior art are solved.
Preferably, the data acquiring module 10 in the embodiment of the present invention includes a lane flow acquiring unit 101, a lane speed acquiring unit 102, a number-of-overtaking acquiring unit 103, and a risk number acquiring unit 104.
The lane flow acquiring unit 101 is configured to select one camera from a plurality of cameras arranged at different positions on each highway section, assign an ID to each vehicle from a video captured by the selected camera by using a target tracking method, and acquire the lane flow on each lane within a preset time period according to the ID and the position of the vehicle.
The highway section is a one-way section without a fork on the highway.
The preset time period in this embodiment is one hour. In other embodiments, the implementer may select a suitable preset time period according to actual situations.
In the embodiment, a target tracking method based on deep learning is adopted, and specifically, a DeepSORT target tracking model is adopted. In other embodiments, the implementer may select an appropriate target tracking model based on the circumstances.
The lane speed obtaining unit 102 is configured to average speeds of a plurality of vehicles measured at one position on each lane in a preset time period to obtain an average vehicle speed, and then average the average vehicle speeds obtained at intervals in the extending direction of each road section to obtain a lane speed.
The overtaking number acquiring unit 103 is configured to obtain the overtaking number according to the vehicle sequence acquired at intervals in the extending direction of each road segment.
And comparing the sequence of the vehicles shot by every two adjacent cameras on a high-speed road section to obtain the overtaking times.
And the risk data acquisition unit 104 is used for acquiring the violation times and the accident times of each road section from the highway monitoring system.
Preferably, the trend correlation acquiring module 20 in the embodiment of the present invention includes a first correlation acquiring unit 201 and a second correlation acquiring unit 202.
The first correlation obtaining unit 201 is configured to obtain a first correlation matrix of the lane flows in one period by using a correlation coefficient method, and average correlations between the lane flows in the first correlation matrix to obtain a first correlation.
One cycle in this embodiment is one day. In other embodiments, the implementer may select the appropriate cycle duration based on the circumstances.
The specific steps for obtaining the first correlation are as follows:
(1) A first matrix shaped as [ n,24] is derived from the lane traffic, where n represents the number of lanes for the road segment and 24 represents the traffic per hour of the day.
(2) And acquiring a first correlation matrix corresponding to the first matrix by adopting a correlation coefficient method, wherein the numerical value of elements in the first correlation matrix is between [ -1,1], a strong negative correlation is represented by-1, a strong positive correlation is represented by +1, and no relation is represented by 0.
(3) Calculating a first correlation according to the elements in the first correlation matrix, wherein the calculation formula is as follows:
where CC1 is the first correlation, CC1 i For traffic flow between the ith and first laneAnd (4) correlation.
The second correlation obtaining unit 202 is configured to obtain a second correlation matrix of lane speeds in a day by using a correlation coefficient method, and obtain a second correlation by averaging correlations between lane speeds in the second correlation matrix.
(1) A second matrix shaped [ n,24] is derived from the lane speeds, where n represents the number of lanes for the road segment and 24 represents the lane speed per hour of the day.
(2) And (3) acquiring a second correlation matrix corresponding to the second matrix by using a correlation coefficient method, wherein the numerical values of elements in the second correlation matrix are between [ -1,1], a strong negative correlation is represented by-1, a strong positive correlation is represented by +1, and no relation is represented by 0.
(3) And calculating a second correlation according to the elements in the second correlation matrix, wherein the calculation formula is as follows:
where CC2 is the second correlation, CC2 i Is the correlation of lane speed between the ith lane and the first lane.
The correlation coefficient method in this embodiment is a Pearson correlation coefficient method. In other embodiments, the implementer may select a suitable correlation coefficient method according to actual circumstances.
The calculation formula of the trend correlation is as follows:
CC3＝w1*CC1+w2*CC2
where CC3 is a trend correlation, the larger CC3 indicates the more crowded the link, w1 is a weight of the first correlation CC1, and w2 is a weight of the second correlation CC 2.
In this embodiment, w1=0.29 and w2=0.71. In other embodiments, the implementer may select the appropriate weights based on the circumstances.
Preferably, the link priority value acquiring module 30 in the embodiment of the present invention includes a correlation acquiring unit 301 and a road curvature degree acquiring unit 302.
A correlation obtaining unit 301, configured to obtain a correlation between the perception data and the risk data by using a typical correlation analysis method. The greater the correlation, the more relevant the perception data is to the road segment risk.
The road curvature degree obtaining unit 302 is configured to obtain the road curvature degree B according to a ratio between the straight distance d between the two end points of each link and the total route s.
The calculation formula of the link priority value is as follows:
LV＝B*(CC4+CC3)
where LV is the link priority value and CC4 is the correlation.
Preferably, the road segment score obtaining module 40 in the embodiment of the present invention includes a long-range correlation obtaining unit 401 and a road segment score calculating unit 402.
The long-range correlation obtaining unit 401 is configured to obtain Hurst indexes h reflecting long-range correlations corresponding to lane flow, lane speed, and the number of overtaking from the historical sensing data by using an elimination trend fluctuation analysis method.
(1) When 0.5 < h < 1, the time series is shown to have long-range correlation, and a state with continuously enhanced trend is shown, namely, the time series is in an increasing (decreasing) trend in a certain time period and is in an increasing (decreasing) trend in the next time period, and the closer h is to 1, the stronger the long-range correlation is.
(2) When h =0.5, it is stated that the time sequence is not relevant and is an independent random process, i.e. the current state does not affect the future state.
(3) When 0 < h < 0.5, the time sequence only has negative correlation and presents a state of reverse persistence, namely the time sequence has a trend of increasing (decreasing) in a certain time period and has a trend of decreasing (increasing) in the next time period.
And the road section score calculation and acquisition unit 402 is used for calculating road section scores according to the Hurst indexes, the road section priority values, the frequency and the time corresponding to the sensing data.
The initial score calculation formula is as follows:
S0＝(h 1 +h 2 +h 3 )*100
wherein S0 is an initial score, h 1 For traffic flowHurst index, h 2 Hurst index, h, corresponding to lane speed 3 The Hurst index corresponding to the lane speed.
The road section score calculation formula is as follows:
Score＝S0+10*LV+0.001*VV-T
wherein, score is the Score of the road section, VV is the frequency of the road section data being accessed in one hour, and T is the distance data generated for T hours.
Preferably, the data caching module 50 in the embodiment of the present invention uses a distributed cache, and when the cache space is insufficient, the data with the lowest road segment score is preferentially released. The cache elimination mode can improve the cache hit rate and avoid the cache penetration problem.
The distributed cache can read data with high performance, can dynamically expand cache nodes, can automatically discover and switch fault nodes, can automatically balance data partitions, can provide a graphical management interface for a user, and is very convenient to deploy and maintain.
Referring to fig. 2, preferably, in order to more reasonably utilize the storage resources and improve the data reading rate when the data in the data cache module 50 is not hit, the highway data efficient storage system 100 in the embodiment of the present invention further includes a data storage module 60, configured to store the data released by the data cache module; in the released data, the data with high road section scores are stored in the outer circle of the magnetic disk, and the data with low road section scores are stored in the inner circle of the magnetic disk.
When the data in the data cache module accessed by the user is not hit, the needed data is searched in the data storage module and is further transmitted to the data cache module.
It should be noted that: the sequence of the above embodiments of the present invention is only for description, and does not represent the advantages or disadvantages of the embodiments. And that specific embodiments have been described above. Other embodiments are within the scope of the following claims. In some cases, the actions or steps recited in the claims can be performed in a different order than in the embodiments and still achieve desirable results. In addition, the processes depicted in the accompanying figures do not necessarily require the particular order shown, or sequential order, to achieve desirable results. In some embodiments, multitasking and parallel processing may also be possible or may be advantageous.
All the embodiments in the present specification are described in a progressive manner, and the same and similar parts among the embodiments are referred to each other, and each embodiment focuses on the differences from other embodiments.
The present invention is not limited to the above embodiments, and any modifications, equivalent substitutions, improvements, etc. within the spirit and principle of the present invention should be included in the protection scope of the present invention.
Claims (7)
1. A computer vision based highway data efficient storage system, comprising:
the data acquisition module is used for acquiring perception data and risk data in a preset time period on each road section; the perception data comprises lane flow, lane speed and overtaking times; the risk data comprises violation times and accident times;
the trend correlation acquisition module is used for respectively acquiring a first correlation of lane flow and a second correlation of lane speed between lanes in a period by adopting a correlation coefficient method and acquiring a trend correlation according to the first correlation and the second correlation;
the road section priority value acquisition module is used for obtaining a road section priority value according to the correlation between the perception data and the risk data in a period, the trend correlation and the road bending degree of each road section;
the road section score acquisition module is used for acquiring the Hurst index of long-range correlation of historical sensing data and acquiring the score of each road section by combining the road section priority value, the road section data access frequency and the time;
the data caching module is used for caching data according to the score of each road section, and preferentially releasing the data with the lowest score of the road sections when the caching space is insufficient;
the road section score calculation formula is as follows:
Score＝S0+10*LV+0.001*VV-T
wherein, the Score is a road section Score, the VV is a road section data access frequency of the road section data accessed in one hour, T is a distance data generation time T hour, and LV is a road section priority value;
S0＝(h1+h2+h3)*100
wherein S0 is an initial score, h1 is a Hurst index corresponding to the traffic flow of the lane, h2 is a Hurst index corresponding to the speed of the lane, and h3 is a Hurst index corresponding to the speed of the lane.
2. The computer vision-based high-efficiency highway data storage system according to claim 1, further comprising a data storage module for storing the data released by the data caching module; and in the released data, the data with high road section scores are stored at the outer circle of the disk, and the data with low road section scores are stored at the inner circle of the disk.
3. The computer vision-based highway data efficient storage system of claim 1 wherein said data acquisition module comprises:
the lane flow acquiring unit is used for acquiring the lane flow by adopting a target tracking method;
the lane speed acquisition unit is used for averaging the speeds of a plurality of vehicles measured at one position on each lane in the preset time period to obtain an average vehicle speed, and then averaging the average vehicle speeds obtained at intervals in the extension direction of each road section to obtain the lane speed;
and the overtaking number acquiring unit is used for acquiring the overtaking number according to the vehicle sequence acquired at intervals in the extending direction of each road section.
4. The computer vision-based highway data efficient storage system of claim 1 wherein said trend correlation acquisition module comprises:
the first correlation obtaining unit is used for obtaining a first correlation matrix of the lane flow in a period by adopting a correlation coefficient method, and averaging the correlation between each lane flow in the first correlation matrix to obtain the first correlation;
and the second correlation obtaining unit is used for obtaining a second correlation matrix of the lane speeds in a period by adopting the correlation coefficient method, and averaging the correlation between each lane speed in the second correlation matrix to obtain the second correlation.
5. The computer vision-based efficient storage system for highway data according to claim 1, wherein said road section priority value obtaining module comprises:
a correlation obtaining unit, configured to obtain a correlation between the perception data and the risk data by using a canonical correlation analysis method;
and the road bending degree acquisition unit is used for obtaining the road bending degree according to the ratio of the linear distance between the two end points of each road section to the total route.
6. The computer vision-based efficient highway data storage system according to claim 1 or 5 wherein said link priority value is the product of the sum of said trend correlation and said correlation and the degree of curvature of said road.
7. The computer vision-based efficient highway data storage system according to claim 1 wherein said segment score acquisition module comprises a long-range correlation acquisition unit for acquiring Hurst indices reflecting long-range correlations of said lane flow, said lane speed and said number of overtaking from historical perception data, respectively, using an elimination trend fluctuation analysis.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110561075.7A CN113345224B (en) | 2021-05-20 | 2021-05-20 | Highway data high efficiency storage system based on computer vision |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110561075.7A CN113345224B (en) | 2021-05-20 | 2021-05-20 | Highway data high efficiency storage system based on computer vision |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113345224A CN113345224A (en) | 2021-09-03 |
| CN113345224B true CN113345224B (en) | 2023-01-10 |
Family
ID=77470922
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110561075.7A Active CN113345224B (en) | 2021-05-20 | 2021-05-20 | Highway data high efficiency storage system based on computer vision |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113345224B (en) |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| DE102012021919A1 (en) * | 2012-11-09 | 2014-05-15 | ITK Engineering AG | Model-based efficiency scoring in the automotive industry |
| CN106897826A (en) * | 2017-02-23 | 2017-06-27 | 吉林大学 | A kind of street accidents risks appraisal procedure and system |
| CN107545729A (en) * | 2017-08-25 | 2018-01-05 | 华南理工大学 | A kind of traffic network Distributed Area control method based on data-driven |
| CN108647905A (en) * | 2018-05-25 | 2018-10-12 | 江西锦路科技开发有限公司 | A kind of highway electromechanics operation management system and management method |
| CN109703564A (en) * | 2017-10-25 | 2019-05-03 | 罗伯特·博世有限公司 | For determining method and apparatus, the computer program of the runway state of vehicle |
| CN210295557U (en) * | 2019-05-31 | 2020-04-10 | 上海车轮互联网服务有限公司 | Auxiliary scoring system for road test |
| US10733105B1 (en) * | 2017-04-17 | 2020-08-04 | EMC IP Holding Company LLC | Method for pipelined read optimization to improve performance of reading data from data cache and storage units |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109118773B (en) * | 2018-09-30 | 2019-10-01 | 中交第一公路勘察设计研究院有限公司 | A kind of traffic accidents methods of risk assessment |
-
2021
- 2021-05-20 CN CN202110561075.7A patent/CN113345224B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| DE102012021919A1 (en) * | 2012-11-09 | 2014-05-15 | ITK Engineering AG | Model-based efficiency scoring in the automotive industry |
| CN106897826A (en) * | 2017-02-23 | 2017-06-27 | 吉林大学 | A kind of street accidents risks appraisal procedure and system |
| US10733105B1 (en) * | 2017-04-17 | 2020-08-04 | EMC IP Holding Company LLC | Method for pipelined read optimization to improve performance of reading data from data cache and storage units |
| CN107545729A (en) * | 2017-08-25 | 2018-01-05 | 华南理工大学 | A kind of traffic network Distributed Area control method based on data-driven |
| CN109703564A (en) * | 2017-10-25 | 2019-05-03 | 罗伯特·博世有限公司 | For determining method and apparatus, the computer program of the runway state of vehicle |
| CN108647905A (en) * | 2018-05-25 | 2018-10-12 | 江西锦路科技开发有限公司 | A kind of highway electromechanics operation management system and management method |
| CN210295557U (en) * | 2019-05-31 | 2020-04-10 | 上海车轮互联网服务有限公司 | Auxiliary scoring system for road test |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113345224A (en) | 2021-09-03 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Liang et al. | Local semantic siamese networks for fast tracking | |
| CN111860693A (en) | Lightweight visual target detection method and system | |
| CN102201065B (en) | Method for detecting monitored video abnormal event based on trace analysis | |
| CN103325259B (en) | A kind of parking offense detection method based on multi-core parallel concurrent | |
| CN113401143A (en) | Individualized self-adaptive trajectory prediction method based on driving style and intention | |
| CN104484673A (en) | Data complementation method for pattern recognition application of real-time data flow | |
| CN105487061A (en) | Multi-characteristic information fusion method for target data correlation | |
| US20220166813A1 (en) | Extrema-retentive data buffering and simplification | |
| CN113129335B (en) | Visual tracking algorithm and multi-template updating strategy based on twin network | |
| CN113345224B (en) | Highway data high efficiency storage system based on computer vision | |
| CN113330278B (en) | Navigation device, navigation method and related equipment | |
| CN111832576A (en) | Lightweight target detection method and system for mobile terminal | |
| CN116244072A (en) | GPGPU micro-architecture system for fence synchronization | |
| CN102238215A (en) | Living guide data processing method, service center and system for vehicle-mounted system | |
| CN114104006A (en) | Method and device for automatically driving vehicle to realize vehicle crossing by mistake | |
| Lu et al. | A New Siamese Heterogeneous Convolutional Neural Networks Based on Attention Mechanism and Feature Pyramid | |
| Wang et al. | Informative image selection for crowdsourcing-based mobile location recognition | |
| CN113674329A (en) | Vehicle driving behavior detection method and system | |
| CN113420942A (en) | Sanitation truck real-time route planning method based on deep Q learning | |
| CN112601050A (en) | Smart city video monitoring method and device | |
| CN110188581A (en) | Based on the multi-fork query tree RFID anti-collision method for improving Manchester's code | |
| CN112083877B (en) | Data grouping method for cloud storage system of vehicle Internet of things | |
| CN105096598B (en) | Method for predicting remaining travel time of vehicle | |
| CN115171378B (en) | High-precision detection tracking method for long-distance multiple vehicles based on road side radar | |
| CN109612467A (en) | Trajectory simplification method, system and track visualization system |
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 | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20221222 Address after: 908, block a, floor 8, No. 116, Zizhuyuan Road, Haidian District, Beijing 100089 Applicant after: ZHONGZI DATA CO.,LTD. Applicant after: CHINA HIGHWAY ENGINEERING CONSULTING Corp. Address before: 450000 No. 6, Zone C, building 2, No. 85, Jinshui East Road, Zhengzhou area (Zhengdong), pilot Free Trade Zone, Zhengzhou City, Henan Province Applicant before: Henan Shuoxiang Information Technology Co.,Ltd. |
|
| TA01 | Transfer of patent application right | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |