CN109166336B - Real-time road condition information acquisition and pushing method based on block chain technology - Google Patents
Real-time road condition information acquisition and pushing method based on block chain technology Download PDFInfo
- Publication number
- CN109166336B CN109166336B CN201811218517.2A CN201811218517A CN109166336B CN 109166336 B CN109166336 B CN 109166336B CN 201811218517 A CN201811218517 A CN 201811218517A CN 109166336 B CN109166336 B CN 109166336B
- Authority
- CN
- China
- Prior art keywords
- test
- road condition
- picture
- road
- descriptors
- 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
Images
Classifications
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/09—Arrangements for giving variable traffic instructions
- G08G1/0962—Arrangements for giving variable traffic instructions having an indicator mounted inside the vehicle, e.g. giving voice messages
- G08G1/0968—Systems involving transmission of navigation instructions to the vehicle
- G08G1/096805—Systems involving transmission of navigation instructions to the vehicle where the transmitted instructions are used to compute a route
- G08G1/096827—Systems involving transmission of navigation instructions to the vehicle where the transmitted instructions are used to compute a route where the route is computed onboard
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
-
- 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
- G06V20/54—Surveillance or monitoring of activities, e.g. for recognising suspicious objects of traffic, e.g. cars on the road, trains or boats
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/09—Arrangements for giving variable traffic instructions
- G08G1/0962—Arrangements for giving variable traffic instructions having an indicator mounted inside the vehicle, e.g. giving voice messages
- G08G1/0968—Systems involving transmission of navigation instructions to the vehicle
- G08G1/096877—Systems involving transmission of navigation instructions to the vehicle where the input to the navigation device is provided by a suitable I/O arrangement
- G08G1/096883—Systems involving transmission of navigation instructions to the vehicle where the input to the navigation device is provided by a suitable I/O arrangement where input information is obtained using a mobile device, e.g. a mobile phone, a PDA
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10016—Video; Image sequence
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30236—Traffic on road, railway or crossing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30242—Counting objects in image
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30248—Vehicle exterior or interior
- G06T2207/30252—Vehicle exterior; Vicinity of vehicle
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Radar, Positioning & Navigation (AREA)
- Remote Sensing (AREA)
- Theoretical Computer Science (AREA)
- Multimedia (AREA)
- Quality & Reliability (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Traffic Control Systems (AREA)
Abstract
The invention relates to the technical field of traffic road conditions, in particular to a real-time road condition information acquisition and pushing method based on a block chain technology, which comprises the following steps of 1) installing road condition application software on a vehicle-mounted terminal or a driver mobile phone by a running vehicle, and acquiring a real-time road condition video of a current road through a driving recorder connected with the vehicle-mounted terminal or the driver mobile phone; 2) processing the road condition video through a video processing module of the road condition application software to acquire the road condition of the running vehicle; 3) updating the road condition conditions to a road condition query module of the road condition application software through a road condition updating module of the road condition application software; 4) the vehicle owner inquires the road condition through the road condition inquiry module to select a proper driving path. The real-time road condition information acquisition and pushing method can fully utilize social public resources, participates in the acquisition of road traffic road condition data through social public, is high in efficiency, and is more flexible than a traditional mechanism.
Description
Technical Field
The invention relates to the technical field of traffic road conditions, in particular to a real-time road condition information acquisition and pushing method based on a block chain technology.
Background
With the rapid development of national economy and the accelerated pace of life, more and more people choose to use vehicles to replace walking when going out, which leads to the increasingly congested urban traffic, and the traditional traffic management mechanism cannot meet the current traffic situation of large passenger flow and large vehicle flow. Traditional real-time road condition information collection system sets up monitored control system at each road section generally, perhaps sets up speed monitor etc. its road condition information's collection, issue, to the renewal again, all manage and control totally by the traffic department, and this kind of information acquisition method not only need consume a large amount of manpowers, material resources on the installation of equipment, and inefficiency, real-time poor moreover.
Moreover, the conventional real-time traffic information collecting system usually needs a central platform to integrate and process the collected information, and as the data volume increases, the efficiency of the system decreases and a lot of difficulties in management occur. Therefore, how to collect traffic condition information in real time and transmit the information to each traffic participant in time is a problem that needs to be solved urgently at present.
Disclosure of Invention
The invention provides a real-time road condition information acquisition and pushing method based on a block chain technology, aiming at the problems in the prior art.
The technical scheme adopted by the invention for solving the technical problems is as follows: a real-time road condition information acquisition and pushing method based on a block chain technology comprises the following steps,
step 1) installing road condition application software on a vehicle-mounted terminal or a driver mobile phone by a running vehicle, and acquiring a real-time road condition video of a current road through a driving recorder connected with the vehicle-mounted terminal or the driver mobile phone;
step 2) processing the road condition video through a video processing module of the road condition application software to acquire the road condition of the running vehicle;
step 3) updating the road condition conditions to a road condition query module of the road condition application software through a road condition updating module of the road condition application software;
and 4) the vehicle owner inquires the road condition through the road condition inquiry module to select a proper driving path.
Preferably, the step 2) specifically includes, 21) segmenting the road condition video in real time at a time interval of 20 seconds to obtain a short road condition video;
22) extracting S frames of pictures to be detected of the road condition short video at equal intervals;
23) detecting the number of vehicles in each frame of picture to be detected and the distance between the running vehicle and the vehicle in front in each frame of picture to be detected, if the number of vehicles in the picture to be detected is greater than a threshold value of the number of vehicles and the distance between the running vehicle and the vehicle in front in each frame of picture to be detected is less than a threshold value of the distance between the running vehicle and the vehicle, judging the road condition of the running vehicle to be a first congestion, otherwise judging the running vehicle to be not a congestion;
24) if 95% of the S frames of the pictures to be detected judge the road condition of the running vehicle as first congestion, judging the road condition of the running vehicle as second congestion, otherwise, judging the running vehicle as not congested;
25) and if the road condition of the running vehicle is judged to be the second congestion by the three continuous short road condition videos, judging the road condition of the running vehicle to be the third congestion, otherwise, judging the running vehicle not to be congested.
Preferably, in the step 3), the traffic condition application software further includes a navigation module, and when the traffic condition of the running vehicle is determined to be third congestion, the traffic condition update module combines with the navigation module to display the running vehicle in the form of a red bright spot on the traffic condition query module.
Preferably, the step 23) of calculating the number of vehicles in the picture to be detected by a background difference method specifically includes the following steps,
231) a road background library is arranged on a cloud server, and the cloud server is connected with the vehicle-mounted terminal or a driver mobile phone;
232) calling a primary road background map corresponding to the position of the running vehicle according to a navigation module;
233) combining the primary road background picture with the picture to be detected and obtaining a final road background picture through a background calculation model;
234) the picture to be detected is subtracted from the final road background picture to obtain a vehicle picture;
235) and counting the number of vehicles of the vehicle pictures.
Preferably, the background calculation model is established through a road background training set and is perfected through a road background test set, and the road background training set and the road background test set are deduplicated by a descriptor matching method, specifically comprising the following steps,
l1, extracting the characteristic points of all pictures in the road background training set, and calculating the descriptors of the corresponding pictures according to the characteristic points;
l2, sequentially extracting a test picture in the road background test set, calculating test feature points of the test picture, and calculating a test descriptor of the test picture according to the test feature points;
l3, obtaining N candidate pictures which are most similar to the test pictures in the road background training set according to the test descriptors and a DBOW algorithm;
l4, selecting a candidate picture from the N candidate pictures in sequence, matching the descriptor of the candidate picture with the test descriptor of the test picture, if the matching result is the same, deleting the test picture in the test set and returning to the step 2), otherwise, continuing to execute the step 4) until the N candidate pictures are matched and returning to the step 2).
Preferably, the matching process in the step L4 is specifically that,
l41, violently matching the test descriptor of the test picture with the descriptor of the candidate picture, and acquiring a test descriptor set integrating the test picture and the candidate picture descriptor;
l42, deleting the test descriptors in the test descriptor set I, wherein the distance between the test descriptors and the nearest test descriptor is larger than a certain threshold value D to obtain a test descriptor set II;
l43, deleting the test descriptors in the second test descriptor set which do not conform to the rotation invariance to obtain a third test descriptor set;
l44, deleting the test descriptors in the third test descriptor set which do not conform to the invariance of scaling to obtain a fourth test descriptor set;
l45, calculating the number of the test descriptors in the fourth test descriptor set, and entering the next step when the number is larger than a threshold value M, otherwise, judging that the matching results of the test picture and the candidate picture are different;
l46. judging whether the test descriptor in the test descriptor set four is matched with the watermark, if so, judging that the matching results of the test picture and the candidate picture are not the same, otherwise, judging that the matching results of the test picture and the candidate picture are the same.
Preferably, the distance between the two test descriptors in the step L42 is modulo of the difference between the two test descriptors;
in the step L43, the rotation invariance is that a test included angle formed between a certain test descriptor in the second set of test descriptors and any other two test descriptors is equal to an included angle formed by descriptors corresponding to the candidate picture.
Preferably, the scaling invariance calculation process in the step L44 is specifically,
l441 pairing any two test descriptors in the test descriptor set III to form a plurality of groups of test descriptors;
l442 calculating a test distance between two test descriptors in each group of test descriptors and calculating a candidate distance between descriptors in the candidate picture corresponding to each group of test descriptors;
l443 calculating the ratio between each group of test distances and the corresponding candidate distance, and calculating the ratio average of all ratios;
l444, the ratio obtained by each group of test descriptors is differentiated from the average value of the ratios, and when the difference is greater than a certain threshold, the two test descriptors of the group do not conform to the invariance of scaling.
Preferably, the step L46 is specifically to calculate an average value of distances between two test descriptors in the fourth set of test descriptors, and if the average value is less than 10% of the diagonal length of the test picture, it is determined that the test descriptors in the fourth set of test descriptors match the watermark, otherwise, it is determined that the test descriptors in the fourth set of test descriptors do not match the watermark.
Preferably, the value of N in the N candidate pictures is 5, the value of the threshold D is 30, and the value of the threshold M is 10.
The real-time road condition information acquisition pushing method has the advantages that social public resources can be fully utilized, social public participates in acquisition of road condition data of road traffic, the efficiency is high, and the method is more flexible than a traditional mechanism; the invention can save a central platform in the traditional sense, and each traffic participant can directly participate in the acquisition process of the road condition information by using the automobile data recorder in the forms of distributed data storage and point-to-point transmission.
Drawings
Fig. 1 is a flowchart of a method for acquiring and pushing real-time traffic information based on a block chain technology according to the present invention.
Detailed Description
The technical scheme of the invention is further explained by the specific implementation mode in combination with the attached drawings.
As shown in fig. 1, a method for acquiring and pushing real-time traffic information based on a block chain technology includes the following steps,
step 1) installing road condition application software on a vehicle-mounted terminal or a driver mobile phone by a running vehicle, and acquiring a real-time road condition video of a current road through a driving recorder connected with the vehicle-mounted terminal or the driver mobile phone.
And 2) processing the road condition video through a video processing module of the road condition application software to acquire the road condition of the running vehicle. The video processing module only processes road condition videos collected by corresponding running vehicles. Specifically, 21) segmenting the road condition video in real time at 20 second time intervals to obtain a short road condition video. 22) And extracting S frames of the road condition short video to-be-detected pictures at equal intervals. 23) And detecting the number of vehicles in each frame of picture to be detected and the distance between the running vehicle and the vehicle in front in each frame of picture to be detected, if the number of vehicles in the picture to be detected is greater than a vehicle number threshold value and the distance between the running vehicle and the vehicle in front in each frame of picture to be detected is less than a vehicle distance threshold value, judging the road condition of the running vehicle to be the first congestion, otherwise, judging the running vehicle to be not congested. The vehicle number threshold may be 5 vehicles and the vehicle distance threshold may be 4 meters. 24) And if 95% of the S frames of the pictures to be detected judge the road condition of the running vehicle as the first congestion, judging the road condition of the running vehicle as the second congestion, otherwise, judging the running vehicle as not congested. 25) And if the road condition of the running vehicle is judged to be the second congestion by the three continuous short road condition videos, judging the road condition of the running vehicle to be the third congestion, otherwise, judging the running vehicle not to be congested.
And 3) updating the road condition in a road condition query module of the road condition application software through a road condition updating module of the road condition application software. The road condition application software further comprises a navigation module, and when the road condition of the running vehicle is judged to be the third congestion, the road condition updating module combines with the navigation module to display the running vehicle in the road condition query module in the form of a red bright spot. The traffic update module updates the latest traffic information of the corresponding running vehicle to all traffic application software. The running vehicles with the first crowded road condition, the second crowded road condition and the non-crowded road condition are not displayed, only the running vehicles with the third crowded road condition are displayed in the road condition query module in the form of red bright spots, and when the road condition of the same running vehicle is changed from the third crowded road condition to other road conditions, the corresponding red bright spots disappear.
And 4) the vehicle owner inquires the road condition through the road condition inquiry module to select a proper driving path. The vehicle owner can inquire the road condition information of the relevant road through the road condition inquiry module, for example, when a red bright spot of a certain road section is more, the vehicle owner can select other roads to drive.
The step 23) of calculating the number of vehicles in the picture to be detected by a background difference method specifically comprises the following steps,
231) and a road background library is arranged on a cloud server, and the cloud server is connected with the vehicle-mounted terminal or a driver mobile phone. 232) And calling a primary road background map corresponding to the position of the running vehicle according to a navigation module. The same road background map is used in a certain range in the same road section and the same lane. 233) And combining the primary road background picture with the picture to be detected and obtaining a final road background picture through a background calculation model. And optimizing the primary road background picture through the background calculation model and the information of the picture to be detected to obtain a final road background picture. The background calculation model collects the existing model. 234) And subtracting the picture to be detected from the final-level road background picture to obtain a vehicle picture. 235) And counting the number of vehicles of the vehicle pictures.
The background calculation model is established through a road background training set and is perfected through a road background test set, the road background training set and the road background test set are deduplicated through a descriptor matching method, and an overfitting phenomenon is avoided, and the method specifically comprises the following steps of L1. extracting characteristic points of all pictures in the road background training set, and calculating descriptors of corresponding pictures according to the characteristic points.
L2, extracting a test picture in the road background test set in sequence, calculating the test feature points of the test picture, and calculating the test descriptor of the test picture according to the test feature points.
L3, acquiring N candidate pictures which are most similar to the test pictures in the road background training set according to the test descriptor and the DBOW algorithm, accelerating the matching speed of the descriptor by using the DBOW algorithm, wherein the number of the pictures in the road background training set is hundreds of thousands, and the number of the road background testing set is tens of thousands.
L4, selecting a candidate picture from the N candidate pictures in sequence, matching the descriptor of the candidate picture with the test descriptor of the test picture, if the matching result is the same, deleting the test picture in the test set and returning to the step 2), otherwise, continuing to execute the step 4) until the N candidate pictures are matched and returning to the step 2).
The matching process in the step L4 is specifically L41. the test descriptor of the test picture and the descriptor of the candidate picture are subjected to violent matching, and the test descriptor set matched by the test picture and the descriptor of the candidate picture is obtained as a whole.
L42 test descriptors in the first set of test descriptors with a distance greater than a threshold D from the nearest test descriptor are removed to obtain a second set of test descriptors in step L42 the distance between the two test descriptors is modulo the difference between the two test descriptors, which removes individual matching feature points.
L43, deleting the test descriptor not conforming to the rotation invariance in the second set of test descriptors to obtain a third set of test descriptors, wherein the rotation invariance in step L43 is that the test included angle formed between one test descriptor in the second set of test descriptors and any two other test descriptors is equal to the included angle formed by the descriptors corresponding to the candidate picture, for example, the candidate picture has feature point 1, feature point 2 and feature point 3, the three feature points are connected to form triangle 1, the test picture has test feature point 1, test feature point 2 and test feature point 3, the three test feature points are connected to form triangle 2, and feature point 1 is matched with test feature point 1, feature point 2 is matched with test feature point 2, feature point 3 is matched with test feature point 3, and if the candidate picture is the same as the test picture, the shapes of triangle 1 and triangle 2 are the same, otherwise, the shapes of triangle 1 and triangle 2 are different with a high probability.
L, deleting the test descriptors which do not conform to the scaling invariance in the third test descriptor set to obtain a fourth test descriptor set, wherein the scaling invariance calculation process in the step L is specifically that L pairs any two test descriptors in the third test descriptor set to form a plurality of groups of test descriptors, L442 calculates the test distance between two test descriptors in each group of test descriptors and calculates the candidate distance between the descriptors in the candidate picture corresponding to each group of test descriptors, 36443 calculates the ratio between each group of test distances and the corresponding candidate distances and calculates the average value of the ratio of all the ratios, L444 makes the difference between the ratio calculated by each group of test descriptors and the average value of the ratio, and when the difference value is greater than a certain threshold value, the two test descriptors in the group do not conform to the scaling invariance.
For example, candidate picture has feature point d1, feature point d2, feature point d3 and feature point d4, test picture has test feature point s1, test feature point s2, test feature point s3 and test feature point s4, and feature point d1 matches with test feature point s1, feature point d2 matches with test feature point s2, feature point d3 matches with test feature point s3, and feature point d4 matches with test feature point s4, where the distance between test feature point s1 and test feature point s2 is the ratio 1 to the distance between feature point d1 and feature point d2, and the distance between test feature point s3 and test feature point s4 is the ratio 2 to the distance between feature point d3 and feature point d4, and if the candidate picture is the same as the test picture, the ratio 1 and the ratio 2 are the same. The invention firstly obtains the average value of the ratio, and then compares the actual ratio with the average ratio to judge whether the descriptor of the tested characteristic point is really matched with the descriptor of the candidate picture.
L45, calculating the number of the test descriptors in the test descriptor set IV, entering the next step when the number is larger than a threshold value M, otherwise, judging that the matching results of the test picture and the candidate picture are different.
L judging whether the test descriptor in the fourth test descriptor set is matched with the watermark or not, if so, judging that the matching result of the test picture and the candidate picture is not the same, otherwise, judging that the matching result of the test picture and the candidate picture is the same, and step L specifically calculating an average value of distances between every two test descriptors in the fourth test descriptor set, if the average value is less than 10% of the diagonal length of the test picture, judging that the test descriptor in the fourth test descriptor set is matched with the watermark, otherwise, judging that the test descriptor in the fourth test descriptor set is not matched with the watermark.
In the N candidate pictures, the value of N may be 5, the value of the threshold D may be 30, and the value of the threshold M may be 10.
The above-described embodiments are merely illustrative of the preferred embodiments of the present invention and do not limit the spirit and scope of the present invention. Various modifications and improvements of the technical solutions of the present invention may be made by those skilled in the art without departing from the design concept of the present invention, and the technical contents of the present invention are all described in the claims.
Claims (2)
1. A real-time road condition information acquisition and pushing method based on a block chain technology is characterized in that: comprises the following steps of (a) carrying out,
step 1) installing road condition application software on a vehicle-mounted terminal or a driver mobile phone by a running vehicle, and acquiring a real-time road condition video of a current road through a driving recorder connected with the vehicle-mounted terminal or the driver mobile phone;
step 2) processing the road condition video through a video processing module of the road condition application software to acquire the road condition of the running vehicle;
step 3) updating the road condition conditions to a road condition query module of the road condition application software through a road condition updating module of the road condition application software;
step 4), the vehicle owner inquires the road condition through the road condition inquiry module to select a proper driving path;
the step 2) specifically comprises the steps of 21) segmenting the road condition video in real time at a time interval of 20 seconds to obtain a short road condition video;
22) extracting S frames of pictures to be detected of the road condition short video at equal intervals;
23) detecting the number of vehicles in each frame of picture to be detected and the distance between the running vehicle and the vehicle in front in each frame of picture to be detected, if the number of vehicles in the picture to be detected is greater than a threshold value of the number of vehicles and the distance between the running vehicle and the vehicle in front in each frame of picture to be detected is less than a threshold value of the distance between the running vehicle and the vehicle, judging the road condition of the running vehicle to be a first congestion, otherwise judging the running vehicle to be not a congestion;
24) if 95% of the S frames of the pictures to be detected judge the road condition of the running vehicle as first congestion, judging the road condition of the running vehicle as second congestion, otherwise, judging the running vehicle as not congested;
25) judging the road condition of the running vehicle to be a third congestion if the road condition of the running vehicle is judged to be the second congestion by the three continuous short road condition videos, or judging the road condition of the running vehicle to be not congested;
in the step 3), the road condition application software further includes a navigation module, and when the road condition of the running vehicle is judged to be the third congestion, the road condition updating module combines with the navigation module to display the running vehicle in the road condition query module in the form of a red bright spot;
the step 23) of calculating the number of vehicles in the picture to be detected by a background difference method specifically comprises the following steps,
231) a road background library is arranged on a cloud server, and the cloud server is connected with the vehicle-mounted terminal or a driver mobile phone;
232) calling a primary road background map corresponding to the position of the running vehicle according to a navigation module;
233) combining the primary road background picture with the picture to be detected and obtaining a final road background picture through a background calculation model;
234) the picture to be detected is subtracted from the final road background picture to obtain a vehicle picture;
235) counting the number of vehicles in the vehicle pictures;
the background calculation model is established through a road background training set and is perfected through a road background test set, and the road background training set and the road background test set are deduplicated through a descriptor matching method, which specifically comprises the following steps,
l1, extracting the characteristic points of all pictures in the road background training set, and calculating the descriptors of the corresponding pictures according to the characteristic points;
l2, sequentially extracting a test picture in the road background test set, calculating test feature points of the test picture, and calculating a test descriptor of the test picture according to the test feature points;
l3, obtaining N candidate pictures which are most similar to the test pictures in the road background training set according to the test descriptors and a DBOW algorithm;
l4, selecting a candidate picture from the N candidate pictures in sequence, matching the descriptor of the candidate picture with the test descriptor of the test picture, if the matching result is the same, deleting the test picture in the test set and returning to the step L2, otherwise, continuing to execute the step L4 until the N candidate pictures are matched and returning to the step L2;
the matching process in the step L4 is specifically that,
l41, violently matching the test descriptor of the test picture with the descriptor of the candidate picture, and acquiring a test descriptor set integrating the test picture and the candidate picture descriptor;
l42, deleting the test descriptors in the test descriptor set I, wherein the distance between the test descriptors and the nearest test descriptor is larger than a certain threshold value D to obtain a test descriptor set II;
l43, deleting the test descriptors in the second test descriptor set which do not conform to the rotation invariance to obtain a third test descriptor set;
l44, deleting the test descriptors in the third test descriptor set which do not conform to the invariance of scaling to obtain a fourth test descriptor set;
l45, calculating the number of the test descriptors in the fourth test descriptor set, and entering the next step when the number is larger than a threshold value M, otherwise, judging that the matching results of the test picture and the candidate picture are different;
l46. judging whether the test descriptor in the test descriptor set four is matched with the watermark, if so, judging that the matching results of the test picture and the candidate picture are different, otherwise, judging that the matching results of the test picture and the candidate picture are the same;
the distance between the two test descriptors in said step L42 is modulo the difference between the two test descriptors;
in the step L43, the rotation invariance is that a test included angle formed between a certain test descriptor in the second test descriptor set and any two other test descriptors is equal to an included angle formed by descriptors corresponding to the candidate picture;
the scaling invariance calculation process in step L44 is specifically,
l441 pairing any two test descriptors in the test descriptor set III to form a plurality of groups of test descriptors;
l442 calculating a test distance between two test descriptors in each group of test descriptors and calculating a candidate distance between descriptors in the candidate picture corresponding to each group of test descriptors;
l443 calculating the ratio between each group of test distances and the corresponding candidate distance, and calculating the ratio average of all ratios;
l444, making the difference between the ratio obtained by each group of test descriptors and the average value of the ratio, when the difference is larger than a certain threshold, the two test descriptors of the group do not accord with the scaling invariance;
the step L46 is specifically to calculate an average value of distances between two test descriptors in the fourth test descriptor set, and if the average value is less than 10% of the diagonal length of the test picture, it is determined that the test descriptors in the fourth test descriptor set match the watermark, otherwise, it is determined that the test descriptors in the fourth test descriptor set do not match the watermark.
2. The method for acquiring and pushing the real-time traffic information based on the block chain technology as claimed in claim 1, wherein: and N values of the N candidate pictures are 5, the threshold value D is 30, and the threshold value M is 10.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811218517.2A CN109166336B (en) | 2018-10-19 | 2018-10-19 | Real-time road condition information acquisition and pushing method based on block chain technology |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811218517.2A CN109166336B (en) | 2018-10-19 | 2018-10-19 | Real-time road condition information acquisition and pushing method based on block chain technology |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109166336A CN109166336A (en) | 2019-01-08 |
| CN109166336B true CN109166336B (en) | 2020-08-07 |
Family
ID=64878423
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811218517.2A Active CN109166336B (en) | 2018-10-19 | 2018-10-19 | Real-time road condition information acquisition and pushing method based on block chain technology |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109166336B (en) |
Families Citing this family (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112820120B (en) * | 2020-12-30 | 2022-03-01 | 杭州趣链科技有限公司 | Multi-party traffic flow space-time cross validation method based on alliance chain |
| CN113347243A (en) * | 2021-05-31 | 2021-09-03 | 重庆工程职业技术学院 | Driving information recording system and method based on block chain |
| CN114973744B (en) * | 2022-05-10 | 2024-04-26 | 江苏国科北斗智能研究院有限公司 | Public travel passenger flow and road condition real-time analysis system based on blockchain |
Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102231236A (en) * | 2011-06-14 | 2011-11-02 | 汉王科技股份有限公司 | Method and device for counting vehicles |
| CN102663894A (en) * | 2012-05-20 | 2012-09-12 | 杭州妙影微电子有限公司 | Road traffic condition foreknowing system and method based on internet of things |
| CN103310206A (en) * | 2013-07-06 | 2013-09-18 | 中国科学技术大学 | Moped detection method based on multi-feature and multi-frame information fusion |
| CN104636488A (en) * | 2015-02-26 | 2015-05-20 | 北京奇艺世纪科技有限公司 | Method and device for determining duplicate video files on basis of pictures |
| CN104851295A (en) * | 2015-05-22 | 2015-08-19 | 北京嘀嘀无限科技发展有限公司 | Method and system for acquiring road condition information |
| CN105469612A (en) * | 2016-01-22 | 2016-04-06 | 大连楼兰科技股份有限公司 | Traffic jam alarming system and traffic jam alarming method |
| CN105787943A (en) * | 2016-03-03 | 2016-07-20 | 西安电子科技大学 | SAR image registration method based on multi-scale image block characteristics and sparse expression |
| CN106297297A (en) * | 2016-11-03 | 2017-01-04 | 成都通甲优博科技有限责任公司 | Traffic jam judging method based on degree of depth study |
| CN106844726A (en) * | 2017-02-10 | 2017-06-13 | 深圳前海大造科技有限公司 | A kind of image-recognizing method matched with violence based on words tree retrieval |
| CN106874445A (en) * | 2017-02-10 | 2017-06-20 | 深圳前海大造科技有限公司 | High in the clouds image-recognizing method based on words tree retrieval with similarity checking |
| CN108564565A (en) * | 2018-03-12 | 2018-09-21 | 华南理工大学 | A kind of power equipment infrared image multi-target orientation method based on deep learning |
Family Cites Families (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US7813870B2 (en) * | 2006-03-03 | 2010-10-12 | Inrix, Inc. | Dynamic time series prediction of future traffic conditions |
| KR101034364B1 (en) * | 2008-10-07 | 2011-05-16 | 현대엠엔소프트 주식회사 | Traffic information generation system and method for intersection road considering enterance and exit |
| CN101853486B (en) * | 2010-06-08 | 2012-06-13 | 华中科技大学 | Image copying detection method based on local digital fingerprint |
| CN106375771B (en) * | 2016-08-31 | 2019-05-24 | 西安万像电子科技有限公司 | Image Feature Matching method and apparatus |
-
2018
- 2018-10-19 CN CN201811218517.2A patent/CN109166336B/en active Active
Patent Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102231236A (en) * | 2011-06-14 | 2011-11-02 | 汉王科技股份有限公司 | Method and device for counting vehicles |
| CN102663894A (en) * | 2012-05-20 | 2012-09-12 | 杭州妙影微电子有限公司 | Road traffic condition foreknowing system and method based on internet of things |
| CN103310206A (en) * | 2013-07-06 | 2013-09-18 | 中国科学技术大学 | Moped detection method based on multi-feature and multi-frame information fusion |
| CN104636488A (en) * | 2015-02-26 | 2015-05-20 | 北京奇艺世纪科技有限公司 | Method and device for determining duplicate video files on basis of pictures |
| CN104851295A (en) * | 2015-05-22 | 2015-08-19 | 北京嘀嘀无限科技发展有限公司 | Method and system for acquiring road condition information |
| CN105469612A (en) * | 2016-01-22 | 2016-04-06 | 大连楼兰科技股份有限公司 | Traffic jam alarming system and traffic jam alarming method |
| CN105787943A (en) * | 2016-03-03 | 2016-07-20 | 西安电子科技大学 | SAR image registration method based on multi-scale image block characteristics and sparse expression |
| CN106297297A (en) * | 2016-11-03 | 2017-01-04 | 成都通甲优博科技有限责任公司 | Traffic jam judging method based on degree of depth study |
| CN106844726A (en) * | 2017-02-10 | 2017-06-13 | 深圳前海大造科技有限公司 | A kind of image-recognizing method matched with violence based on words tree retrieval |
| CN106874445A (en) * | 2017-02-10 | 2017-06-20 | 深圳前海大造科技有限公司 | High in the clouds image-recognizing method based on words tree retrieval with similarity checking |
| CN108564565A (en) * | 2018-03-12 | 2018-09-21 | 华南理工大学 | A kind of power equipment infrared image multi-target orientation method based on deep learning |
Non-Patent Citations (2)
| Title |
|---|
| Vehicle traffic congestion management in vehicular ad-hoc networks;Brijesh Kadri Mohandas，Ramiro Liscano，Oliver W. W. Yang;《2009 IEEE 34th Conference on Local Computer Networks》;IEEE;20091023;第655-660页 * |
| 无人机视觉导航关键技术的研究与实现;尤宇星;《中国优秀硕士学位论文全文数据库 工程科技II辑》;20180215(第02期);第25-38页第三章节 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109166336A (en) | 2019-01-08 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN104751631B (en) | The method that Trip chain mode of transportation is judged based on GPS location and fuzzy theory | |
| CN108986465B (en) | Method, system and terminal equipment for detecting traffic flow | |
| Morishita et al. | SakuraSensor: Quasi-realtime cherry-lined roads detection through participatory video sensing by cars | |
| CN110351651B (en) | Vehicle track missing identification and compensation method | |
| CN109754594A (en) | A kind of road condition information acquisition method and its equipment, storage medium, terminal | |
| CN109166336B (en) | Real-time road condition information acquisition and pushing method based on block chain technology | |
| CN107784835A (en) | Traffic behavior model prediction system and its Forecasting Methodology based on traffic data analyzing | |
| CN112863172A (en) | Highway traffic running state judgment method, early warning method, device and terminal | |
| CN113155173B (en) | Perception performance evaluation method and device, electronic device and storage medium | |
| CN111127949B (en) | Vehicle high-risk road section early warning method and device and storage medium | |
| CN112837542B (en) | Method and device for counting traffic volume of highway section, storage medium and terminal | |
| CN112562330A (en) | Method and device for evaluating road operation index, electronic equipment and storage medium | |
| CN110322687B (en) | Method and device for determining running state information of target intersection | |
| CN112734242A (en) | Method and device for analyzing availability of vehicle running track data, storage medium and terminal | |
| CN107590999A (en) | A kind of traffic state judging method based on bayonet socket data | |
| CN110021161B (en) | Traffic flow direction prediction method and system | |
| CN110827537B (en) | Method, device and equipment for setting tidal lane | |
| CN114329074B (en) | Traffic energy efficiency detection method and system for ramp road section | |
| CN108447257B (en) | Web-based traffic data analysis method and system | |
| CN114997493A (en) | Method and system for predicting carbon emission of vehicles on highway | |
| CN111767644B (en) | Method for estimating actual traffic capacity of expressway road section by considering speed limit influence of single tunnel | |
| CN115440037B (en) | Traffic flow data acquisition method and device, electronic equipment and storage medium | |
| CN110782671A (en) | Real-time updating method and server for road congestion state | |
| CN110349428A (en) | Whether identification user is going to the method and device of bus station | |
| CN113393011B (en) | Method, device, computer equipment and medium for predicting speed limit information |
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 |