CN111899389A - Method for identifying vehicle type and license plate of fleet management system - Google Patents
Method for identifying vehicle type and license plate of fleet management system Download PDFInfo
- Publication number
- CN111899389A CN111899389A CN202010732306.1A CN202010732306A CN111899389A CN 111899389 A CN111899389 A CN 111899389A CN 202010732306 A CN202010732306 A CN 202010732306A CN 111899389 A CN111899389 A CN 111899389A
- Authority
- CN
- China
- Prior art keywords
- license plate
- plate information
- consistent
- information
- vehicle
- 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.)
- Granted
Links
Images
Classifications
-
- G—PHYSICS
- G07—CHECKING-DEVICES
- G07C—TIME OR ATTENDANCE REGISTERS; REGISTERING OR INDICATING THE WORKING OF MACHINES; GENERATING RANDOM NUMBERS; VOTING OR LOTTERY APPARATUS; ARRANGEMENTS, SYSTEMS OR APPARATUS FOR CHECKING NOT PROVIDED FOR ELSEWHERE
- G07C9/00—Individual registration on entry or exit
- G07C9/20—Individual registration on entry or exit involving the use of a pass
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/60—Type of objects
- G06V20/62—Text, e.g. of license plates, overlay texts or captions on TV images
-
- 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
- G08G1/017—Detecting movement of traffic to be counted or controlled identifying vehicles
- G08G1/0175—Detecting movement of traffic to be counted or controlled identifying vehicles by photographing vehicles, e.g. when violating traffic rules
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/60—Type of objects
- G06V20/62—Text, e.g. of license plates, overlay texts or captions on TV images
- G06V20/625—License plates
Abstract
The invention discloses a method for identifying vehicle types and license plates by a fleet management system, which comprises the following steps: s01: when a vehicle enters a vehicle crossing, the entrance camera shoots a license plate image B and transmits the license plate image B to an entrance recognition center; the entrance recognition center obtains license plate information B; s02: the vehicle type recognition camera shoots a vehicle image and transmits the vehicle image to a vehicle type recognition center; the vehicle type recognition center obtains vehicle type information; s03: the vehicle is driven out of the vehicle crossing, and the license plate image A is shot by the exit camera and is transmitted to the exit recognition center; the exit recognition center obtains license plate information A; s04: and the license plate information B, the vehicle type information and the license plate information A are transmitted to a control center, and the control center adopts a self-adaptive intelligent checking and matching algorithm to obtain accurate license plate information C and vehicle type information. The invention can greatly improve the accuracy of license plate recognition and vehicle type recognition, and can be widely applied to various systems for vehicle management.
Description
Technical Field
The invention relates to the field of motorcade relationship systems, in particular to a method for identifying vehicle types and license plates by a motorcade management system.
Background
With the popularization of private cars and the wide application of intelligent management systems, license plate recognition and vehicle type recognition become the most important and basic parts in vehicle management systems, and further application and operation of the vehicle management systems are required to be established on the basis of license plate recognition and vehicle type recognition.
In the prior art, the license plate recognition technology adopts a method for directly recognizing license plate images, and under the conditions of large traffic flow and small inter-vehicle distance, the license plate images are difficult to shoot, so that vehicle missing or repeated shooting is easily caused, and further, the recognition system is caused to repeatedly recognize or miss vehicles. In addition, in the prior art, the vehicle type identification and the license plate identification are independent from each other and cannot be verified mutually.
Particularly, when vehicle identification is carried out at a high-speed toll station, license plate identification and vehicle type identification are closely associated with the receiving and sending card, if repeated identification or vehicle leakage occurs, the receiving and sending card is caused to have problems, and the vehicle passing efficiency of the toll station is seriously influenced.
In addition, in the prior art, many factors such as vehicle speed, external environment, position of a license plate in a vehicle, license plate recognition algorithm and the like can cause that license plate recognition and vehicle type recognition can not reach high enough accuracy.
Disclosure of Invention
The invention aims to provide a fleet management system and a method for identifying vehicle types and license plates thereof.
In order to achieve the purpose, the invention adopts the following technical scheme: a method for identifying vehicle types and license plates by a fleet management system comprises the following steps:
s01: when a vehicle enters a vehicle crossing, the entrance camera shoots a license plate image B and transmits the license plate image B to an entrance recognition center; the entrance recognition center calculates the license plate image B to obtain license plate information B; wherein the entrance recognition center recognizes less than or equal to 2 license plate information B within M seconds; m is greater than 0;
s02: the vehicle type recognition camera shoots a vehicle image and transmits the vehicle image to a vehicle type recognition center; the vehicle type recognition center calculates the vehicle image to obtain vehicle type information;
s03: the vehicle is driven out of the vehicle crossing, and the license plate image A is shot by the exit camera and is transmitted to the exit recognition center; the exit recognition center calculates the license plate image A to obtain license plate information A; the exit identification center identifies at least 3 license plate information A within 2M seconds;
s04: and the license plate information B, the vehicle type information and the license plate information A are transmitted to a control center, and the control center adopts a self-adaptive intelligent checking and matching algorithm to obtain accurate license plate information C and vehicle type information.
Further, the license plate information B comprises license plate information B1 and license plate information B2, and the license plate information A comprises license plate information A1, license plate information A2 and license plate information A3;
if the license plate information B1 is consistent with the license plate information A1, and the license plate information B2 is consistent with the license plate information A2, the license plate information C is consistent with the license plate information B1;
if the license plate information B1 is consistent with the license plate information A1, and the license plate information B2 is consistent with the license plate information A3, the license plate information C is consistent with the license plate information B1;
if the license plate information B1 is consistent with the license plate information A2, and the license plate information B2 is consistent with the license plate information A3, the license plate information C is consistent with the license plate information B1;
if only the license plate information B2 is consistent with the license plate information A1, the license plate information C is consistent with the license plate information B2;
if only the license plate information B1 is consistent with the license plate information A1, the license plate information C is consistent with the license plate information B1.
Further, the license plate information B comprises license plate information B1 and license plate information B2, and the license plate information A comprises license plate information A1 and license plate information A2;
if the license plate information B1 is consistent with the license plate information A1, and the license plate information B2 is consistent with the license plate information A2, the license plate information C is consistent with the license plate information B1;
if the license plate information B1 is consistent with the license plate information A2 and the license plate information B1 is empty, the license plate information C is consistent with the license plate information B2; if the license plate information B1 is consistent with the license plate information A2 and the license plate information B1 is not empty, otherwise, the license plate information C is consistent with the license plate information B1;
and if the license plate information B1, the license plate information B2, the license plate information A1 and the license plate information A2 are inconsistent, the license plate information C is consistent with the license plate information A1.
Further, the license plate information B comprises license plate information B1 and license plate information B2, and the license plate information A comprises license plate information A1;
if the license plate information B1 is consistent with the license plate information A1, the license plate information C is consistent with the license plate information B1;
if the license plate information B1 is consistent with the license plate information A2, the license plate information C is consistent with the license plate information B1;
if the license plate information B2 is consistent with the license plate information A1, the license plate information C is consistent with the license plate information B2;
and if the license plate information B1 and the license plate information B2 are not consistent with the license plate information A1, the license plate information C is consistent with the license plate information B1.
Further, when the license plate information B comprises license plate information B1 and license plate information B2, the license plate information A is empty; the license plate information C is consistent with the license plate information B1;
when the license plate information B comprises license plate information B1, the license plate information A is empty; the license plate information C coincides with the license plate information B1.
Further, the license plate information B comprises license plate information B1, and the license plate information A comprises license plate information A1, license plate information A2 and license plate information A3;
if the license plate information B1 is consistent with the license plate information A1, the license plate information C is consistent with the license plate information B1;
if the license plate information B1 is consistent with the license plate information A2 and the license plate information A1 is empty, the license plate information C is consistent with the license plate information B1; if the license plate information B1 is consistent with the license plate information A2 and the license plate information A1 is not empty, the license plate information C is consistent with the license plate information A1;
if the license plate information B1 is consistent with the license plate information A3, comparingComparing time differences among adjacent license plate information in the license plate information A1, the license plate information A2 and the license plate information A3, wherein if the time differences are smaller than a time threshold, the license plate information C is consistent with the license plate information A3; if the license plate information B1 is consistent with the license plate information A3, comparing time differences between adjacent license plate information in the license plate information A1, the license plate information A2 and the license plate information A3, and if at least one time difference is larger than a time threshold, comparing the time difference A between the license plate information A1 and the license plate information A221If the time difference A21If the time threshold value is smaller than the time threshold value, the license plate information C is consistent with the license plate information A2; otherwise, the license plate information C is consistent with the license plate information A1;
and if the license plate information B1 is not consistent with the license plate information A1, the license plate information A2 and the license plate information A3, comparing time differences among adjacent license plate information in the license plate information A1, the license plate information A2 and the license plate information A3, and if the time differences are smaller than a time threshold value, determining that the license plate information C is consistent with the license plate information A1.
Further, the license plate information B comprises license plate information B1, and the license plate information A comprises license plate information A1 and license plate information A2;
if the license plate information B1 is consistent with the license plate information A1, the license plate information C is consistent with the license plate information B1;
if the license plate information B1 is consistent with the license plate information A2, the license plate information C is consistent with the license plate information B1;
and if the license plate information B1 is not consistent with the license plate information A1 and the license plate information A2, the license plate information C is consistent with the license plate information A1.
Further, the license plate information B comprises license plate information B1, and the license plate information A comprises license plate information A1;
if the license plate information B1 is consistent with the license plate information A1, the license plate information C is consistent with the license plate information B1;
if the license plate information B1 is inconsistent with the license plate information A1 and the license plate information B1 is empty, the license plate information C is consistent with the license plate information A1; if the license plate information B1 is inconsistent with the license plate information A1 and the license plate information B1 is not empty, the license plate information C is consistent with the license plate information B1;
further, in the step S02, an included angle between a view center line of the vehicle type recognition camera and a lane is an arbitrary value between 80 degrees and 100 degrees, the vehicle type recognition camera shoots M frames of vehicle images, the recognition center firstly splices the M frames of vehicle images into a complete vehicle side view, and then performs vehicle type recognition according to the vehicle side view.
Further, in the step S04, the control center obtains accurate license plate information C by using a self-adaptive intelligent checking and matching algorithm according to the license plate information B and the license plate information a; and the control center compares and checks the license plate information C and the vehicle type information, and if the license plate information C and the vehicle type information are consistent, the license plate information C and the vehicle type information are output.
The invention has the following beneficial effects: the method comprises the steps that an inlet camera and an inlet recognition center are adopted to obtain license plate information B, an outlet camera and an outlet recognition center are adopted to obtain license plate information A, accurate license plate information C is obtained through a self-adaptive intelligent checking matching algorithm, and the license plate information C and vehicle type information are compared and verified; the invention can greatly improve the accuracy of license plate recognition and vehicle type recognition, and can be widely applied to various systems for vehicle management.
Drawings
FIG. 1 is a schematic view of an apparatus of a fleet management system in embodiment 1;
FIG. 2 is a schematic view of an apparatus of a fleet management system in embodiment 2;
FIG. 3 is a schematic view of an apparatus of a fleet management system in embodiment 3;
in the figure: lane left edge 101, lane right edge 102, vehicle 103, exit identification module 104, vehicle type identification module 105, and entrance identification module 106.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, embodiments of the present invention are described in detail below with reference to the accompanying drawings.
As shown in fig. 1-3, the device for improving the accuracy of license plate recognition at the lane entrance provided by the invention comprises a control center, an entrance camera positioned at the lane entrance, an entrance recognition center, a vehicle type recognition camera, a vehicle type recognition center, an exit camera positioned at the lane exit, and an exit recognition center. Preferably, the entrance camera and the entrance recognition center may be integrated in the entrance recognition module 106, the exit camera and the exit recognition center may be integrated in the exit recognition module 104, and the vehicle type recognition camera and the vehicle type recognition center may be integrated in the vehicle type recognition module 105.
The entrance recognition module 106, the vehicle type recognition module 105 and the exit recognition module 104 may be disposed on the same side or on two sides of the lane, and may be specifically disposed according to actual requirements. As shown in fig. 1, a schematic diagram of an apparatus in which an entrance recognition module 106, a vehicle type recognition module 105, and an exit recognition module 104 are disposed on the same side of a lane in embodiment 1; as shown in fig. 2, a schematic diagram of an apparatus in which an entrance recognition module 106 is disposed on the right side of a lane and an exit recognition module 104 and a vehicle type recognition module 105 are disposed on the left side of the lane in embodiment 2; as shown in fig. 3, in embodiment 3, the vehicle type recognition module 105 is disposed on the left side of the lane, and the exit recognition module 104 and the entrance recognition module 106 are disposed on the right side of the lane. In addition, the exit recognition module 104, the vehicle type recognition module 105 and the entrance recognition module 106 may be arranged and combined at both sides of the lane.
The entrance camera and the exit camera only need to shoot license plate images, the license plate images can be front license plate images or rear license plate images, and the positions of the license plate images shot by the entrance camera and the exit camera can be specifically set according to actual requirements. In practical application, if the device is used in a vehicle management system such as a toll station and the like which needs to determine the next operation according to license plate information, the license plate image B and the license plate image A are preferably front license plate images, because the entrance camera is over against the entering direction of the vehicle, shooting can be carried out between lanes where the vehicle enters, and the whole recognition time can be saved; the final recognition result is directly determined by the recognition result of the license plate image shot by the exit camera, and further the next operation of the vehicle recognition system is related, so that the license plate information A needs to be obtained before the vehicle exits the lane, and the license plate information A needs to be shot by the exit camera and is also the front license plate information.
The processing process of the license plate image B by the entrance recognition module and the processing process of the license plate image A by the exit recognition module are independent processes, and the algorithms adopted by the entrance recognition module and the exit recognition module are different from each other in the preprocessing operation of the images.
The vehicle type identification module can adopt any vehicle type identification module in the prior art. Preferably, the new regulations of the traffic department stipulate that the high-speed toll needs to be determined according to the vehicle type based on the vehicle length, the axle and the passenger carrying number. Therefore, in the invention, the identifying unit identifies the axles and the length of the vehicle according to the side view of the vehicle, and determines the corresponding vehicle type information according to the passenger capacity of the vehicle, wherein the axles refer to the row number of the axles in the vehicle, and the axles in the same row are overlapped and covered in the side view of the vehicle, so that the number of the identified axles can represent the row number of the axles of the vehicle. The vehicle length can also be determined according to the camera parameters, and the accurate vehicle type information of the vehicle can be obtained by combining the passenger carrying number.
The invention provides a method for improving the accuracy of recognizing a license plate at a lane entrance, which comprises the following steps:
s01: when a vehicle enters a vehicle crossing, the entrance camera shoots a license plate image B and transmits the license plate image B to an entrance recognition center; the entrance recognition center calculates the license plate image B to obtain license plate information B; wherein, the entrance recognition center recognizes less than or equal to 2 license plate information B within M seconds; m is greater than 0. For example, when the entrance recognition center recognizes the license plate information B1 and the license plate information B2, the entrance recognition center transmits the information to the control center, and if the entrance recognition center recognizes only the license plate information B1, the entrance recognition center continues to wait for 5 seconds, and if the entrance recognition center still recognizes only the license plate information B1 after 5 seconds, the license plate information B1 is transmitted to the control center.
S02: the vehicle type recognition camera shoots a vehicle image and transmits the vehicle image to a vehicle type recognition center; and the vehicle type recognition center calculates the vehicle image to obtain vehicle type information X.
Specifically, the included angle between the view center line of the vehicle type identification camera and the lane is an arbitrary value between 80 degrees and 100 degrees, preferably, the view center line of the vehicle type identification camera and the lane is 90 degrees, that is, the vehicle type identification camera is located on one side of the lane, and the view of the vehicle type identification camera cannot cover the side face of the whole vehicle, and the image is shot by the camera M to splice a complete image, wherein the M is an integer greater than 0.
The vehicle type recognition center splices a complete vehicle side view according to the vehicle speed value and the positions of the vehicle head, the vehicle body and the vehicle tail, when splicing, an image of the vehicle head position is taken as a splicing start, an image of the vehicle tail position is taken as a splicing end, then the vehicle running speed and the shooting frame rate of a camera are combined, the same characteristic points are taken as bridges, repeated parts among the same characteristic points are covered, and a splicing subunit splices the vehicle side view from the vehicle head to the vehicle tail; and splicing the side views of the vehicles from the head to the tail of the vehicle by the splicing subunit. The characteristic points are positioned on the same side of the vehicle, and the distances from the side to the camera are equal everywhere; only by ensuring that the positions of the characteristic points in each image used for splicing the images in the actual vehicle are the same as the depth of field of the camera, the spliced images can be ensured to be complete and not deformed. The reason is that in the process of changing the two-dimensional plane graph from the three-dimensional structure of the vehicle to the image, only the characteristic points on the same side face at the same depth position with the camera can be used as a spliced bridge, and the spliced image can accurately reflect the shape of the vehicle.
The vehicle type recognition center recognizes the vehicle type information according to the vehicle side map. The vehicle type identification can be carried out by adopting any identification mode in the prior art.
S03: the vehicle is driven out of the vehicle crossing, and the license plate image A is shot by the exit camera and is transmitted to the exit recognition center; the exit recognition center calculates the license plate image A to obtain license plate information A; wherein, the exit identification center identifies less than or equal to 3 license plate information A within 2M seconds. For example, when the exit recognition center recognizes the license information a1, the license information a2, and the license information A3, the exit recognition center transmits the license information a1, the license information a2, and the license information A3 to the control center, and if the entrance recognition center recognizes only the license information a1 and/or the license information a2, the entrance recognition center continues to wait for 10 seconds, and if the entrance recognition center still recognizes only the license information a1 and/or the license information a2, the license information a1 and/or the license information a2 is transmitted to the control center.
The values are explained in the invention, license plate images shot by the inlet camera and the outlet camera comprise time stamps of shooting moments, the time stamps also exist along with license plate information B and license plate information A, and when the control center comprehensively judges the license plate information B and the license plate information A, the source of the license plate information and a corresponding calculation algorithm can be determined according to the time stamps in the license plate information B and the license plate information A.
S04: and the license plate information B, the vehicle type information X and the license plate information A are transmitted to a control center, and the control center adopts a self-adaptive intelligent checking and matching algorithm to obtain accurate license plate information C and vehicle type information X. The license plate information C and the vehicle type information D are compared and verified, and the verification process is as follows: firstly, judging whether license plate information C and vehicle type information D are output in the period of time, and if both license plate information C and vehicle type information D are output, binding the license plate information C and the vehicle type information D; secondly, if the license plate obtained from the license plate information C identification result comprises colors and characters, the type of the vehicle is obviously different from that of the license plate information D according to the license plate big data statistical rule, for example, the license plate information C is a yellow plate, and the vehicle type information D is a passenger vehicle or a cargo vehicle I; at the moment, ignoring the vehicle type recognition result, determining the vehicle type according to the axle of the vehicle, specifically, if the axle is less than or equal to 2, uniformly judging that the vehicle type is a second cargo; if the axle is equal to 3, uniformly judging that the vehicle type is cargo three; if the axle is equal to 4, uniformly judging that the vehicle type is cargo four; if the axle is equal to 5, uniformly judging that the vehicle type is cargo five; if the axle is larger than 6, the vehicle type is judged to be six goods in a unified way. The axle here refers to the number of rows of the vehicle. For another example, if the license plate characters have special car characters, the vehicle type information needs to be identified by the special car.
If the license plate information C is output but the vehicle type information D is not output, a user needs to look into the license plate B; if the number of the entrance license plates B is not increased again in the time period, the exit license plates A1 are repeated, the license plates need to be corrected again, namely, the entrance license plate information A and the exit license plate information B are fed back to the control center again for correction, the license plate information C is assigned again, and the number is regarded as no vehicle processing; if the number of the entrance license plates B in the time period is increased newly, the vehicle type information D is indicated to be corresponding to the missing vehicle, the vehicle type needs to be corrected again, the vehicle type identification is carried out again, the comparison is carried out again, and if the vehicle type information can not be identified again, the vehicle type information D of the vehicle is obtained according to the color and the characters of the license plates and the statistical rule of the large license plate data. The time period in this step refers to a time period during which the vehicle passes between the entrance camera and the exit camera.
If vehicle type information D is output but no vehicle type information C is output, the exit vehicle license A needs to be seen, if the number of the exit vehicle license A in the time period is not increased, repeated recognition of the vehicle corresponding to the vehicle type information D is described, the vehicle type recognition is judged to be invalid, if the number of the exit vehicle license A in the time period is increased, the vehicle leakage phenomenon of the exit vehicle license B is described, the vehicle license information needs to be corrected again, namely, the entry vehicle license information A and the exit vehicle license information B are fed back to the control center again for correction, the vehicle license information C is assigned again, and the vehicle license information C and the vehicle type information D after being assigned again are bound. The time period in this step refers to a time period during which the vehicle passes between the entrance camera and the exit camera.
Specifically, the process of the control center acquiring accurate license plate information C includes the following situations:
(1) the license plate information B comprises license plate information B1 and license plate information B2, and the license plate information A comprises license plate information A1, license plate information A2 and license plate information A3;
if the license plate information B1 is consistent with the license plate information A1, and the license plate information B2 is consistent with the license plate information A2, the license plate information C is consistent with the license plate information B1;
if the license plate information B1 is consistent with the license plate information A1, and the license plate information B2 is consistent with the license plate information A3, the license plate information A2 is a repeated recognition result, and the license plate information C is consistent with the license plate information B1;
if the license plate information B1 is consistent with the license plate information A2, and the license plate information B2 is consistent with the license plate information A3, the license plate information A1 is a repeated recognition result, and the license plate information C is consistent with the license plate information B1;
if only the license plate information B2 is consistent with the license plate information A1, the license plate information B1 is a repeated recognition result, and the license plate information C is consistent with the license plate information B2;
if only the license plate information B1 is consistent with the license plate information A1, it is indicated that a missing vehicle appears behind the license plate information A1, the license plate information C of the current vehicle is consistent with the license plate information B1, and the license plate information C of the next vehicle is consistent with the license plate information B2.
(2) The license plate information B comprises license plate information B1 and license plate information B2, and the license plate information A comprises license plate information A1 and license plate information A2;
if the license plate information B1 is consistent with the license plate information A1, and the license plate information B2 is consistent with the license plate information A2, the license plate information C is consistent with the license plate information B1;
if the license plate information B1 is consistent with the license plate information A2, the license plate information A1 is a repeated recognition result, and the license plate information C is consistent with the license plate information B1;
if the license plate information B2 is consistent with the license plate information A1, the situation that a vehicle is missed before the license plate information A1 or the license plate information B1 is a repeated recognition result is shown, and at the moment, if the license plate information B1 is empty (no license plate), the license plate information C is consistent with the license plate information B2; if the license plate information B1 is not empty, otherwise, the license plate information C is consistent with the license plate information B1;
if the license information B1 and the license information B2 are inconsistent with the license information A1 and the license information A2, the license information B1 and the license information B2 are repeated, and the license information C is consistent with the license information A1.
(3) The license plate information B comprises license plate information B1 and license plate information B2, and the license plate information A comprises license plate information A1;
if the license plate information B1 is consistent with the license plate information A1, the license plate information C is consistent with the license plate information B1;
if the license plate information B2 is consistent with the license plate information A1, the license plate information B1 is a repeated recognition result, and the license plate information C is consistent with the license plate information B2;
if the license plate information B1 and the license plate information B2 are inconsistent with the license plate information A1, the situation that the vehicle is missed before the license plate information A1 is indicated, and the license plate information C is consistent with the license plate information B1.
(4) The license plate information B comprises license plate information B1 and license plate information B2, and the license plate information A is empty; the vehicle missing of the exit recognition center is serious, and the license plate information C is consistent with the license plate information B1.
(5) The license plate information B comprises license plate information B1, and the license plate information A comprises license plate information A1, license plate information A2 and license plate information A3;
if the license plate information B1 is consistent with the license plate information A1, serious vehicle leakage behind the license plate information B1 is indicated, and the license plate information C is consistent with the license plate information B1;
if the license plate information B1 is consistent with the license plate information A2, the situation that the vehicle is missed before the license plate information B1 is indicated, or the repeated recognition result of the license plate information A1 is indicated; at this time, if the license plate information a1 is empty, the license plate information C is consistent with the license plate information B1; if the license plate information A1 is not empty, the license plate information C is consistent with the license plate information A1;
if the license plate information B1 is consistent with the license plate information A3, the situation that the vehicle is seriously missed in the entrance recognition center is shown; comparing time differences among adjacent license plate information in the license plate information A1, the license plate information A2 and the license plate information A3, wherein if the time differences are smaller than a time threshold, the license plate information C is consistent with the license plate information A3; if at least one time difference is larger than the time threshold value, comparing the time difference A between the license plate information A1 and the license plate information A221If the time difference A21If the time threshold value is smaller than the time threshold value, the license plate information C is consistent with the license plate information A2; otherwise, the license plate information C is consistent with the license plate information A1;
and if the license plate information B1 is inconsistent with the license plate information A1, the license plate information A2 and the license plate information A3, comparing time differences among adjacent license plate information in the license plate information A1, the license plate information A2 and the license plate information A3, merging the license plate information A if the time differences are smaller than a time threshold, and enabling the license plate information C to be consistent with the license plate information A. For example, if the time difference between the license plate information a2 and the license plate information a1 is much smaller than the time difference between the license plate information A3 and the license plate information a2, the license plate information C is consistent with the license plate information a 1.
(6) The license plate information B comprises license plate information B1, and the license plate information A comprises license plate information A1 and license plate information A2;
if the license plate information B1 is consistent with the license plate information A1, the license plate information C is consistent with the license plate information B1;
if the license plate information B1 is consistent with the license plate information A2, the license plate information A1 is a repeated recognition result, and the license plate information C is consistent with the license plate information B1;
if the license plate information B1 is inconsistent with the license plate information A1 and the license plate information A2, the result of repeated recognition of the license plate information B1 is shown, and the license plate information C is consistent with the license plate information A1.
(7) The license plate information B comprises license plate information B1, and the license plate information A comprises license plate information A1;
if the license plate information B1 is consistent with the license plate information A1, the license plate information C is consistent with the license plate information B1;
if the license plate information B1 is inconsistent with the license plate information A1, the license plate information B1 is repeated, or the vehicle is missed among the license plate information A1, at the moment, if the license plate information B1 is empty, the license plate information C is consistent with the license plate information A1; if the license plate information B1 is not empty, the license plate information C is consistent with the license plate information B1;
(8) the license plate information B comprises license plate information B1, and the license plate information A is empty; the vehicle is missed at the exit recognition center, and the license plate information C is consistent with the license plate information B1.
The method comprises the steps that an inlet camera and an inlet recognition center are adopted to obtain license plate information B, an outlet camera and an outlet recognition center are adopted to obtain license plate information A, accurate license plate information C is obtained through a self-adaptive intelligent checking matching algorithm, and the license plate information C and vehicle type information are compared and verified; the invention can greatly improve the accuracy of license plate recognition and vehicle type recognition, and can be widely applied to various systems for vehicle management.
The above description is only a preferred embodiment of the present invention, and the embodiment is not intended to limit the scope of the present invention, so that all equivalent structural changes made by using the contents of the specification and the drawings of the present invention should be included in the scope of the appended claims.
Claims (10)
1. A method for identifying vehicle types and license plates by a fleet management system is characterized by comprising the following steps:
s01: when a vehicle enters a vehicle crossing, the entrance camera shoots a license plate image B and transmits the license plate image B to an entrance recognition center; the entrance recognition center calculates the license plate image B to obtain license plate information B; wherein the entrance recognition center recognizes less than or equal to 2 license plate information B within M seconds; m is greater than 0;
s02: the vehicle type recognition camera shoots a vehicle image and transmits the vehicle image to a vehicle type recognition center; the vehicle type recognition center calculates the vehicle image to obtain vehicle type information;
s03: the vehicle is driven out of the vehicle crossing, and the license plate image A is shot by the exit camera and is transmitted to the exit recognition center; the exit recognition center calculates the license plate image A to obtain license plate information A; the exit identification center identifies at least 3 license plate information A within 2M seconds;
s04: and the license plate information B, the vehicle type information and the license plate information A are transmitted to a control center, and the control center adopts a self-adaptive intelligent checking and matching algorithm to obtain accurate license plate information C and vehicle type information.
2. The method of claim 1, wherein the license plate information B comprises license plate information B1 and license plate information B2, and the license plate information A comprises license plate information A1, license plate information A2 and license plate information A3;
if the license plate information B1 is consistent with the license plate information A1, and the license plate information B2 is consistent with the license plate information A2, the license plate information C is consistent with the license plate information B1;
if the license plate information B1 is consistent with the license plate information A1, and the license plate information B2 is consistent with the license plate information A3, the license plate information C is consistent with the license plate information B1;
if the license plate information B1 is consistent with the license plate information A2, and the license plate information B2 is consistent with the license plate information A3, the license plate information C is consistent with the license plate information B1;
if only the license plate information B2 is consistent with the license plate information A1, the license plate information C is consistent with the license plate information B2;
if only the license plate information B1 is consistent with the license plate information A1, the license plate information C is consistent with the license plate information B1.
3. The method of claim 1, wherein the license plate information B comprises license plate information B1 and license plate information B2, and the license plate information A comprises license plate information A1 and license plate information A2;
if the license plate information B1 is consistent with the license plate information A1, and the license plate information B2 is consistent with the license plate information A2, the license plate information C is consistent with the license plate information B1;
if the license plate information B1 is consistent with the license plate information A2 and the license plate information B1 is empty, the license plate information C is consistent with the license plate information B2; if the license plate information B1 is consistent with the license plate information A2 and the license plate information B1 is not empty, otherwise, the license plate information C is consistent with the license plate information B1;
and if the license plate information B1, the license plate information B2, the license plate information A1 and the license plate information A2 are inconsistent, the license plate information C is consistent with the license plate information A1.
4. The method of claim 1, wherein the license plate information B comprises license plate information B1 and license plate information B2, and the license plate information A comprises license plate information A1;
if the license plate information B1 is consistent with the license plate information A1, the license plate information C is consistent with the license plate information B1;
if the license plate information B1 is consistent with the license plate information A2, the license plate information C is consistent with the license plate information B1;
if the license plate information B2 is consistent with the license plate information A1, the license plate information C is consistent with the license plate information B2;
and if the license plate information B1 and the license plate information B2 are not consistent with the license plate information A1, the license plate information C is consistent with the license plate information B1.
5. The method for vehicle type and license plate recognition of the fleet management system according to claim 1, wherein when the license plate information B includes license plate information B1 and license plate information B2, the license plate information a is empty; the license plate information C is consistent with the license plate information B1;
when the license plate information B comprises license plate information B1, the license plate information A is empty; the license plate information C coincides with the license plate information B1.
6. The method of claim 1, wherein the license plate information B comprises license plate information B1, and the license plate information A comprises license plate information A1, license plate information A2 and license plate information A3;
if the license plate information B1 is consistent with the license plate information A1, the license plate information C is consistent with the license plate information B1;
if the license plate information B1 is consistent with the license plate information A2 and the license plate information A1 is empty, the license plate information C is consistent with the license plate information B1; if the license plate information B1 is consistent with the license plate information A2 and the license plate information A1 is not empty, the license plate information C is consistent with the license plate information A1;
if the license plate information B1 is consistent with the license plate information A3, comparing time differences among adjacent license plate information in the license plate information A1, the license plate information A2 and the license plate information A3, and if the time differences are smaller than a time threshold, determining that the license plate information C is consistent with the license plate information A3; if the license plate information B1 is consistent with the license plate information A3, comparing time differences between adjacent license plate information in the license plate information A1, the license plate information A2 and the license plate information A3, and if at least one time difference is larger than a time threshold, comparing the time difference A between the license plate information A1 and the license plate information A221If the time difference A21If the time threshold value is smaller than the time threshold value, the license plate information C is consistent with the license plate information A2; otherwise, the license plate information C is consistent with the license plate information A1;
and if the license plate information B1 is not consistent with the license plate information A1, the license plate information A2 and the license plate information A3, comparing time differences among adjacent license plate information in the license plate information A1, the license plate information A2 and the license plate information A3, and if the time differences are smaller than a time threshold value, determining that the license plate information C is consistent with the license plate information A1.
7. The method of claim 1, wherein the license plate information B comprises license plate information B1, and the license plate information A comprises license plate information A1 and license plate information A2;
if the license plate information B1 is consistent with the license plate information A1, the license plate information C is consistent with the license plate information B1;
if the license plate information B1 is consistent with the license plate information A2, the license plate information C is consistent with the license plate information B1;
and if the license plate information B1 is not consistent with the license plate information A1 and the license plate information A2, the license plate information C is consistent with the license plate information A1.
8. The method of claim 1, wherein the license plate information B comprises license plate information B1, and the license plate information A comprises license plate information A1;
if the license plate information B1 is consistent with the license plate information A1, the license plate information C is consistent with the license plate information B1;
if the license plate information B1 is inconsistent with the license plate information A1 and the license plate information B1 is empty, the license plate information C is consistent with the license plate information A1; if the license plate information B1 is inconsistent with the license plate information A1 and the license plate information B1 is not empty, the license plate information C is consistent with the license plate information B1.
9. The method as claimed in claim 1, wherein in step S02, the included angle between the center line of the field of view of the vehicle type recognition camera and the lane is any value between 80 degrees and 100 degrees, and the vehicle type recognition camera takes M frames of vehicle images, and the recognition center first splices the M frames of vehicle images into a complete vehicle side view, and then performs vehicle type recognition according to the vehicle side view.
10. The method for recognizing the vehicle type and the license plate of the fleet management system according to claim 1, wherein the control center obtains the accurate license plate information C by adopting a self-adaptive intelligent checking and matching algorithm according to the license plate information B and the license plate information a in the step S04; and the control center compares and checks the license plate information C and the vehicle type information, and if the license plate information C and the vehicle type information are consistent, the license plate information C and the vehicle type information are output.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010732306.1A CN111899389B (en) | 2020-07-27 | 2020-07-27 | Method for identifying vehicle type and license plate of fleet management system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010732306.1A CN111899389B (en) | 2020-07-27 | 2020-07-27 | Method for identifying vehicle type and license plate of fleet management system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111899389A true CN111899389A (en) | 2020-11-06 |
| CN111899389B CN111899389B (en) | 2022-06-28 |
Family
ID=73190033
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010732306.1A Active CN111899389B (en) | 2020-07-27 | 2020-07-27 | Method for identifying vehicle type and license plate of fleet management system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111899389B (en) |
Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2014002534A (en) * | 2012-06-18 | 2014-01-09 | Toshiba Corp | Vehicle type determination device and vehicle type determination method |
| CN104392232A (en) * | 2014-11-07 | 2015-03-04 | 北京邮电大学 | Method for correcting video metadata in traffic scenes |
| CN104574977A (en) * | 2013-10-14 | 2015-04-29 | 泓格科技股份有限公司 | Vehicle passing information identification matching system |
| CN106127107A (en) * | 2016-06-14 | 2016-11-16 | 宁波熵联信息技术有限公司 | The model recognizing method that multi-channel video information based on license board information and vehicle's contour merges |
| CN106384537A (en) * | 2016-10-12 | 2017-02-08 | 防城港市港口区升聚科技有限公司 | Parking lot management system based on video technology |
| KR101730465B1 (en) * | 2016-12-19 | 2017-04-27 | 주식회사 디아이랩 | vehicle identification method and system using vale-added information of vehicle |
| CN106710230A (en) * | 2017-01-24 | 2017-05-24 | 杨茂君 | Automatic identifying system and identifying method thereof for motor vehicle model classification |
| CN107122740A (en) * | 2017-04-26 | 2017-09-01 | 南京理工大学 | A kind of vehicle type recognition device and method based on twin camera |
| CN108205897A (en) * | 2016-12-16 | 2018-06-26 | 北京迪科达科技有限公司 | A kind of car plate analysis and identification system of vehicle |
| CN108389396A (en) * | 2018-02-28 | 2018-08-10 | 北京精英智通科技股份有限公司 | A kind of vehicle matching process, device and charge system based on video |
| CN108986242A (en) * | 2018-06-25 | 2018-12-11 | 广州安迪信息技术有限公司 | A kind of secondary Vehicle License Plate Recognition System and method for the not parking mobile payment lane of highway |
-
2020
- 2020-07-27 CN CN202010732306.1A patent/CN111899389B/en active Active
Patent Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2014002534A (en) * | 2012-06-18 | 2014-01-09 | Toshiba Corp | Vehicle type determination device and vehicle type determination method |
| CN104574977A (en) * | 2013-10-14 | 2015-04-29 | 泓格科技股份有限公司 | Vehicle passing information identification matching system |
| CN104392232A (en) * | 2014-11-07 | 2015-03-04 | 北京邮电大学 | Method for correcting video metadata in traffic scenes |
| CN106127107A (en) * | 2016-06-14 | 2016-11-16 | 宁波熵联信息技术有限公司 | The model recognizing method that multi-channel video information based on license board information and vehicle's contour merges |
| CN106384537A (en) * | 2016-10-12 | 2017-02-08 | 防城港市港口区升聚科技有限公司 | Parking lot management system based on video technology |
| CN108205897A (en) * | 2016-12-16 | 2018-06-26 | 北京迪科达科技有限公司 | A kind of car plate analysis and identification system of vehicle |
| KR101730465B1 (en) * | 2016-12-19 | 2017-04-27 | 주식회사 디아이랩 | vehicle identification method and system using vale-added information of vehicle |
| CN106710230A (en) * | 2017-01-24 | 2017-05-24 | 杨茂君 | Automatic identifying system and identifying method thereof for motor vehicle model classification |
| CN107122740A (en) * | 2017-04-26 | 2017-09-01 | 南京理工大学 | A kind of vehicle type recognition device and method based on twin camera |
| CN108389396A (en) * | 2018-02-28 | 2018-08-10 | 北京精英智通科技股份有限公司 | A kind of vehicle matching process, device and charge system based on video |
| CN108986242A (en) * | 2018-06-25 | 2018-12-11 | 广州安迪信息技术有限公司 | A kind of secondary Vehicle License Plate Recognition System and method for the not parking mobile payment lane of highway |
Non-Patent Citations (1)
| Title |
|---|
| 冯帆: "基于序列图像的车身长度尺寸在线测量方法与技术研究", 《中国优秀硕士学位论文全文数据库信息科技辑》 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111899389B (en) | 2022-06-28 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111860384B (en) | Vehicle type recognition method | |
| US6888953B2 (en) | Vehicle surroundings monitoring apparatus | |
| CN106991820B (en) | Illegal vehicle processing method and device | |
| CN104574540A (en) | Electronic toll collection system and method | |
| CN112966582A (en) | Vehicle type three-dimensional recognition method, device and system, electronic equipment and storage medium | |
| US11302110B2 (en) | Pedestrian action recognition and localization using RGB images | |
| CN110232324A (en) | A kind of automatic recognition system and method for expressway tol lcollection vehicle | |
| CN112528807B (en) | Method and device for predicting running track, electronic equipment and storage medium | |
| KR20140027661A (en) | Ticketless toll gate system using plural camera | |
| CN111914678A (en) | Method and device for matching multiple vehicle license plates and storage medium | |
| Gao et al. | On‐line vehicle detection at nighttime‐based tail‐light pairing with saliency detection in the multi‐lane intersection | |
| CN111899389B (en) | Method for identifying vehicle type and license plate of fleet management system | |
| CN110232827B (en) | Free flow toll collection vehicle type identification method, device and system | |
| CN107393311A (en) | A kind of car plate tamper Detection device and method | |
| CN112183206B (en) | Traffic participant positioning method and system based on road side monocular camera | |
| CN111862622B (en) | Device and method for improving identification accuracy of license plate at lane entrance | |
| CN113674442B (en) | Non-inductive passing method, device, electronic equipment and computer readable storage medium | |
| CN207518750U (en) | It is a kind of to be suitable for being directed to traffic offence vehicle license plate identification device on vehicle | |
| CN114078212A (en) | Accurate vehicle type identification method and device based on ETC portal | |
| CN111862364A (en) | Automatic card issuing system and method for toll station | |
| CN112164205B (en) | Method and device for sending alarm information | |
| CN112133108B (en) | Method and device for sending prompt message | |
| CN112164226B (en) | Information storage method and device, storage medium and electronic device | |
| CN111860381A (en) | Axle counting device and method for lane openings | |
| CN113688662A (en) | Motor vehicle passing warning method and device, electronic device and computer equipment |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |