Parking non-inductive payment system based on big data

Abstract

The invention discloses a parking non-inductive payment system based on big data, and the system comprises a central control platform, a speed measurement sensor, a distance judgment module, a holographic projection device, an alarm prompt module, a display screen, a special character judgment module, a similarity monitoring module, an image processing module, a character comparison module, a GPRS positioning module, a database, and a shooting terminal. The license plate number of the vehicle can be accurately recognized through the special character judgment module, the recognition rate of the shooting terminal is improved, the vehicle does not need to be repeatedly scanned during backing up, the vehicle using time of a vehicle owner is saved, and the time for a rear vehicle to drive out of a parking lot is not delayed any more; the license plate number of the vehicle can be recognized by the shooting terminal, the recognition accuracy is improved, and the repeated recognition time is shortened.

Description

Technical Field

[0001] The present invention relates to the technical field of intelligent parking lot charging, and in particular to a parking non-contact payment system based on big data. Background Art

[0002] With the progress and development of modernization, more and more vehicles need to be parked in parking lots at home and abroad. However, due to the excessive number of vehicles, more and more vehicles are often parked at the entrance of the parking lot. Some parking lot entrances are even installed in the urban area, resulting in congestion in the road section, making it impossible for other vehicles to pass. Therefore, nowadays, non-contact payment technology is installed in the parking lot to clear the congestion in the parking lot. The non-contact payment technology is to use the unique feature of the license plate number on the vehicle and bind the bank card and other payment methods for payment. The image recognition technology or other technical recognition is used to identify the license plate number. Through this method, the vehicle can quickly pass through the underground parking lot, reducing the burden of vehicle congestion on the road; However, there are still many problems when using contactless payment. The image received by the background processing is blurred due to the vehicle driving too fast, and the vehicle license plate number cannot be accurately identified. Or due to the wrong identification of the shooting terminal, the parking fee of the vehicle will be deducted from other license plates, increasing the error rate, or the vehicle needs to rescan the license plate number when backing up, which will cause the vehicles behind this vehicle to collide with each other when moving backwards, causing danger. When using contactless payment, since there are many similar characters, the photographing terminal cannot confirm, causing the vehicle to need to be rescanned back and forth, wasting the owner's time. Therefore, it is necessary to improve the scanning accuracy of the photographing terminal. Summary of the invention

[0003] The purpose of the present invention is to provide a parking contactless payment system based on big data to solve the problems raised in the above background technology.

[0004] In order to solve the above technical problems, the present invention provides the following technical solutions: a parking non-sensing payment system based on big data, the system comprising a central control platform, a speed sensor, a distance judgment module, a holographic projection device, an alarm prompt module, a display screen, a special character judgment module, a similarity monitoring module, an image processing module, a character comparison module, a GPRS positioning module, a database and a shooting terminal, the central control platform is used to control the operation process of the entire system and send the received command to the next processing terminal, so that the vehicle can complete the parking payment action, thereby not affecting the time for the rear vehicle to leave the parking lot, the speed sensor is installed on both sides of the parking lot curve, and is used to detect the speed of the vehicle traveling in the lane, so as to It can determine whether the current vehicle needs to reverse again to verify the vehicle's license plate number to ensure the normal passage of the vehicle. The distance judgment module is used to measure the distance between the two sides of the vehicle tires when the vehicle turns, and infer whether the vehicle's license plate number will be scanned according to the current vehicle's offset angle. The holographic projection device is installed on one side of the shooting terminal, and is used to move the route to one side when the vehicle's driving route deviates. When the vehicle's driving route deviates, the route with a larger deviation on one side of the vehicle is moved to one side, so that the vehicle can travel in the set road area and the vehicle's license plate number can be identified, ensuring that the vehicle can normally pay and leave the parking lot without affecting the driving of other vehicles. The alarm prompt module is used to send an alarm to the central control platform when it is detected that the current vehicle is retreating to the rear. The prompt prevents the front vehicle from hitting other vehicles due to the dark light in the parking lot, causing the rear vehicle to be unable to brake and cause danger. The display screen is used to display the license plate number of the current vehicle and determine whether the license plate number of the current vehicle is correct, so that the owner can provide timely feedback. The special character judgment module is used to monitor the undetected characters in the license plate number, and identify the number of special characters in the current characters, and use different methods to identify the license plate number according to the number of special characters. The similarity monitoring module is used to determine the error rate of the current character recognition according to the recognition records stored in the database when it is detected that there is only one special character in the license plate number, and determine the error rate according to the similarity between the current character and other characters. and error rate to determine the current character recognition result, so as to ensure that the current vehicle can pass smoothly. The image processing module is used to process the picture when it detects that there are several special characters in the vehicle number, and judge whether the pixel width of the current character in the picture matches the pixel width corresponding to different characters, so as to determine whether the character judgment on the current vehicle is correct. The character comparison module is used to compare the pixel values ​​between similar letters and numbers, so as to determine whether the current license plate number character is a number or a letter. The GPRS positioning module is used to locate the position of the vehicle in the curve. The database is used to record and save the data of the vehicle parking in the city, so as to retrieve the data in time for analysis.The shooting terminal is used to take pictures of vehicles and license plate numbers, and send the taken pictures to the central control platform for processing, so as to timely understand the current state of the curve.

[0005] Further, it is set that the exit of the current parking lot is in the shape of a curve. The speed received by the speed measurement sensor installed on the roadside of the curve is uploaded to the central control platform, and it is judged that the set of speeds of several driving vehicles is V = {v 1 , v 2 , v 3 ... v n}}. When it is detected that the vehicle speed V i > V p , it means that the current vehicle speed exceeds the normal driving range. Among them, V i refers to the speed of the current vehicle, and V p refers to the set speed threshold. When the current vehicle is turning while driving on the curve, the farthest vertical distance between the current vehicle and one side of the curve is set as d. According to the angles 1 , 2 , 3 ... n formed by the rotation of the current vehicle tire at different positions W = {w }, the curve W formed is set as W = kx + b, where k and b refer to the constants of the curve function, and x refers to the driving time. The central control platform detects that the leftmost position that the shooting module can shoot is H i , and the rightmost position that can be detected is H r . The formed curve is Y = ao 2 + bo + c, where a, b, and c refer to the constants of the curve function Y, o refers to the abscissa, and Y refers to the ordinate. According to the driving trajectory of the vehicle and the final stopping position W k of the current vehicle, it is judged whether the license plate number where the current vehicle finally stops is inside the curve formed by the shooting module. When the shooting terminal can detect the length from the leftmost end to the rightmost end of the license plate number, it means that the vehicle is driving normally in the curve. When the shooting terminal cannot detect the length from the leftmost end to the rightmost end of the license plate number, the holographic projection device is used to move the roadside line that is longer on one side of the vehicle towards the vehicle, forming multiple driving lanes, so that the driver's field of vision can be narrowed and the license plate number of the vehicle can be fully recognized.

[0006] Further, when it is detected that the driving speed v i > v pWhen the license plate number detected on the display screen is half of the license plate characters, the position of the vehicle behind the current vehicle is detected in real time. When the distance between the current vehicle d and the vehicle J behind is greater than the set distance, a path length of R is projected between the front vehicle and the rear vehicle using the holographic projection device, so that the front vehicle can reverse in time and re-verify the license plate number. When the distance between the rear vehicle and the current vehicle is less than the preset distance, the central control module sends a signal to the alarm prompt module to prompt the rear vehicle in time.

[0007] When the vehicle is driving in a curve and the distance between the rear vehicle and the front vehicle is detected to be less than the preset distance, the central control platform prompts the rear vehicle. In the two-dimensional plane, the position of the front vehicle when it has not reversed is P=(a,b). When the license plate number information of the front vehicle is not captured, the front vehicle needs to reverse again. At this time, the position of the vehicle within time t is P’=(a 2 ,b 2 ). When the detected reverse speed e of the front vehicle i is greater than the preset speed e, the rear vehicle needs to move in the opposite direction of the front vehicle to prevent the front vehicle from braking and hitting the rear vehicle. When the detected reverse speed of the front vehicle is less than the preset speed, the rear vehicle only needs to move m meters in the rear direction of the front vehicle, where m refers to the standard distance between the front vehicle and the rear vehicle.

[0008] Furthermore, when it is detected that only half of the license plate characters are displayed on the display screen, and there is a special character among the undetected license plate characters, according to the signal sent by the central control platform to the database, the number of times the vehicle has parked in all parking lots is Q times, and the number of times the vehicle is scanned again by the shooting terminal is Q’. When the accuracy rate of the shooting terminal is lower than the standard accuracy rate, the characters in the current license plate are judged. Let the current two characters be x,y. The photos taken by the image processing module are subjected to grayscale and binarization processing. The position coordinates of the upper left corner of the current character are set as (x,y), and the coordinates of the lower right corner are . The area of the black region in the current two characters is calculated, and it is calculated and judged whether the areas of the black regions are the same. The area difference error rate between the two characters is within . The characters in the license plate are selected according to the area size.

[0009] When the license plate in the picture displayed by the central control platform is tilted, according to the angle formed by the straight line formed by the left lower end coordinate (e, f) and the right lower end coordinate (e’, f’) of the license plate and the straight line formed by the left lower end and the right lower end of the standard license plate, it is adjusted in the direction of the straight line where the standard license plate is located.

[0010] When several special characters are detected in the license plate characters, after the central control platform receives the signal, it performs grayscale processing on the currently detected picture. The steps for processing the current several special characters are as follows: Z01: Selectively frame similar feature characters in the current license plate, set the same length and width pixel values for the framed picture, perform grayscale processing on the current character, and calculate the pixel lengths in the abscissa and ordinate of the current character. Compare the lengths between the starting point at the leftmost end of the pixel width and the ending point at the rightmost end of the pixel width of different character endpoints, and mark the characters with the same pixel width of length as S1; Calculate the pixel ratio occupied by each character, and judge the similarity according to the pixel ratio. The pixel ratio is , where L x refers to the pixel length occupied by white pixels, and L P refers to the length of the sum of white pixels and black pixels; initially judge the differences between different characters through the pixel ratio; Z02: Traverse the pixels of non-license plate characters, and compare the non-license plate traversal results with the license plate pixel traversal results to judge whether the error is within the preset range; Z03: When the result is S1 and the result is within the preset range, traverse the characters with the same pixel width from the leftmost end to the rightmost end of each row of character pixels and from the uppermost end to the lowermost end of each category until all traversals are completed. Send the different pixel lengths represented by different traversal results to the central control platform for comparison and select the corresponding characters.

[0011] Z04: When it is detected that the error is not within the preset range, traverse the characters in the license plate again until the deviation is within the set range.

[0012] When it is detected that the similarity between two or more characters in the license plate number exceeds the standard similarity, record the number of times the current vehicle parks in different parking lots, and save the characteristics of the current license plate number and the corresponding vehicle type in the database to facilitate the shooting terminal to quickly identify the license plate number and quickly pass through the curve.

[0013] Compared with the prior art, the beneficial effects achieved by the present invention are: 1. By installing a holographic projection device, during the user's driving process, when it is detected that the user's route deviates from the shooting terminal and the shooting terminal cannot recognize the user's license plate number, the roadside line that is relatively long on one side of the vehicle is moved towards the vehicle by using holographic projection to form multiple driving lanes, and the license plate number of the vehicle can be fully recognized; 2. By using the special character judgment module, the number of special characters contained in the license plate number is detected and judged. When a special character is detected in the license plate number, the area of ​​the black area in the characters in the license plate number is calculated, and the characters in the license plate are judged according to the area size. When multiple special characters are detected in the license plate number, the characters in the license plate number are gray-scaled, and the pixel lengths of the horizontal and vertical coordinates of the current character are compared and judged. The characters are traversed until the traversal is completed, and the meanings of different characters are judged according to different pixel lengths, thereby enhancing the recognition accuracy of the shooting terminal. BRIEF DESCRIPTION OF THE DRAWINGS

[0014] The accompanying drawings are used to provide a further understanding of the present invention and constitute a part of the specification. Together with the embodiments of the present invention, they are used to explain the present invention and do not constitute a limitation of the present invention. In the accompanying drawings: Figure 1 It is a schematic diagram of the module composition of a parking non-sensing payment system based on big data of the present invention; Figure 2 It is a schematic diagram of special character processing steps of a parking contactless payment system based on big data of the present invention. DETAILED DESCRIPTION

[0015] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0016] See also Figure 1 - Figure 2 , the present invention provides a technical solution: The system includes a central control platform, a speed measurement sensor, a distance judgment module, a holographic projection device, an alarm prompt module, a display screen, a special character judgment module, a similarity monitoring module, an image processing module, a character comparison module, a GPRS positioning module, a database, and a shooting terminal. The central control platform is used to control the operation process of the entire system and send the received commands to the next processing terminal, enabling the vehicle to complete the parking payment action, thus not affecting the time for the vehicle behind to drive out of the parking lot. The speed measurement sensor is installed on both sides of the parking lot curve and is used to detect the speed of the vehicle driving in the lane, so as to determine whether the current vehicle needs to reverse again to verify and detect the license plate number of the vehicle, ensuring the normal passage of the vehicle. The distance judgment module is used to measure the distance between the two sides of the vehicle tires when the vehicle turns and infer whether the license plate number of the vehicle will be scanned according to the offset angle of the current vehicle, so as to ensure that the vehicle can drive in the set road area and the license plate number of the vehicle can be recognized, ensuring that the vehicle can pay and drive out of the parking lot normally without affecting the driving of other vehicles. The alarm prompt module is used to send an alarm prompt by the central control platform when it is detected that the current vehicle is backing up, so that the vehicle in front will not hit other vehicles due to the dim light in the parking lot, resulting in the vehicle behind being unable to brake in time and causing danger. The display screen is used to display the license plate number of the current vehicle and determine whether the license plate number of the current vehicle is correct, so that the vehicle owner can give feedback in time. The special character judgment module is used to monitor the characters not detected in the license plate number, identify the number of special characters contained in the current characters, and use different methods to identify the license plate number according to the number of special characters. The similarity monitoring module is used to judge the error rate of the current character recognition according to the recognition records saved in the database when it is detected that there is only one special character in the license plate number, and determine the current character recognition result according to the similarity judgment and error rate between the current character and other characters, so as to ensure that the current vehicle can pass smoothly. The image processing module is used to process the picture when it is detected that there are several special characters in the vehicle number, and judge whether it matches according to the pixel width of the current character in the picture and the pixel width corresponding to different characters, so as to determine whether the character judgment on the current vehicle is correct. The character comparison module is used to compare the pixel values between similar letters and numbers, so as to judge whether the current license plate number character is a number or a letter. The GPRS positioning module is used to position the vehicle in the curve. The database is used to record and save the parking data of the vehicle in the city, so as to facilitate the timely retrieval of data for analysis. The shooting terminal is used to take pictures of the vehicle and the license plate number and send the taken pictures to the central control platform for processing, so as to timely understand the status of the current curve.

[0017] Set the exit of the current parking lot to be in a curved shape. The speed received by the speed measurement sensor installed on the roadside of the curve is uploaded to the central control platform, and a set of speeds of several moving vehicles is determined as V = {v 1 , v 2 , v 3 ... v n}. When it is detected that the vehicle speed V i > V p , it means that the current vehicle speed exceeds the normal driving range. Among them, V i refers to the speed of the current vehicle, and V p refers to the set speed threshold. When the current vehicle is turning on the curve, set the farthest vertical distance between the current vehicle and one side of the curve to be d. According to the angles 1 , w 2 , w 3 ... w n formed by the rotation of the current vehicle's tires at different positions W = {w }, a curve W is formed. Set W = kx + b, where k and b refer to the constants of the curve function, and x refers to the driving time. The central control platform detects that the leftmost position that the shooting module can shoot is H i , and the rightmost position that can be detected is H r . The formed curve is Y = ao 2 + bo + c, where a, b, and c refer to the constants of the curve function Y, o refers to the abscissa, and Y refers to the ordinate. According to the driving trajectory of the vehicle and the final stop position W k of the current vehicle, determine whether the license plate number where the current vehicle finally stops is inside the curve formed by the shooting module. When the shooting terminal can detect the length from the leftmost end to the rightmost end of the license plate number, it means that the vehicle is driving normally in the curve. When the shooting terminal cannot detect the length from the leftmost end to the rightmost end of the license plate number, use the holographic projection device to move the roadside line that is longer on one side of the vehicle towards the vehicle, forming multiple driving lanes, so as to narrow the driver's field of vision and enable the license plate number of the vehicle to be fully recognized.

[0018] When it is detected that the driving speed v i > v pWhen the license plate number detected on the display screen is half of the license plate characters, the position of the vehicle behind the current vehicle is detected in real time. When the distance between the current vehicle d and the vehicle J behind is greater than the set distance, a path length of R is projected between the front vehicle and the rear vehicle using the holographic projection device, so that the front vehicle can reverse in time and re-verify the license plate number. When the distance between the rear vehicle and the current vehicle is detected to be less than the preset distance, the central control module sends a signal to the alarm prompt module to prompt the rear vehicle in time.

[0019] When the vehicle is driving in a curve and the distance between the rear vehicle and the front vehicle is detected to be less than the preset distance, the central control platform prompts the rear vehicle. In the two-dimensional plane, the position of the front vehicle when it has not reversed is P=(a,b). When the license plate number information of the front vehicle is not captured, the front vehicle needs to reverse again. At this time, the position of the vehicle within time t is P’=(a 2 ,b 2 ). When the detected reverse speed e of the front vehicle i is greater than the preset speed e, the rear vehicle needs to move in the opposite direction of the front vehicle to prevent the front vehicle from braking and hitting the rear vehicle. When the detected reverse speed of the front vehicle is less than the preset speed, the rear vehicle only needs to move m meters in the direction behind the front vehicle, where m refers to the standard distance between the front vehicle and the rear vehicle.

[0020] When the vehicle is driving normally in a curve, due to the friction with the ground, the vehicle will move forward at a normal speed. When the vehicle is reversing, the vehicle speed increases and the curve will cause the vehicle to retreat significantly, which will pose a danger to the vehicle behind. Therefore, a preset value of the speed is set here to judge whether the backward impact when the vehicle is reversing will hit the vehicle behind. When the vehicle slides backward more, the vehicle behind must move in the opposite direction of the reverse of the front vehicle to prevent major accidents. When the vehicle slides backward less, the vehicle behind also needs to keep a distance from the front vehicle to prevent accidents. Here, only the speed of the vehicle driving is considered, and the reasons for the backward movement of the front vehicle in the large environment are removed. For example, due to the fast reverse speed of the front vehicle owner and untimely braking, the vehicle will move backward. Due to the slope of the curve, the downhill speed of the front vehicle is much greater than its own reverse speed, resulting in the vehicle sliding down, or the vehicle slides down significantly due to the inertia of braking on the landslide.

[0021] When it is detected that only half of the license plate characters are displayed on the display screen, and there is a special character among the undetected license plate characters, according to the signal sent by the central control platform to the database, the number of times the vehicle has parked in all parking lots is Q times, and the number of times the vehicle is scanned again by the shooting terminal is Q’. When the accuracy of the shooting terminal is detected When the accuracy rate is lower than the standard, the characters in the current license plate are judged. Assume the current two characters are x and y. The photo taken by the image processing module is subjected to grayscale and binarization processing. Assume the position coordinates of the upper left corner of the current character are (x, y), and the coordinates of the lower right corner are , calculate the area of the black area in the current two characters, calculate and judge whether the areas of the black areas are the same. The area difference error rate between the two characters is , select the characters in the license plate according to the area size.

[0022] Adjust the grayscale value of the background except the character itself in the license plate characters to 0, and adjust the grayscale value of the character itself to 255, so that the characters in the license plate can be obvious. The areas cut by different letters are the same. Calculate according to the black areas formed in different characters to form different areas, so that the characters in the license plate can be clearly recognized. The area of the black area can be directly calculated through the set coordinates, making the calculation result more accurate; When calculating the black area in the current character, first judge the characters that are misrecognized and correctly recognized in the database each time. By comparing the black areas of these two characters, the final character is judged; Among them, the special characters are '0', 'D', 'O', 'B', '8', '1', 'I', '5', 'S', etc. The similarity of these characters is relatively high. Therefore, it is necessary to distinguish and compare such characters.

[0023] When the license plate in the picture displayed on the central control platform is tilted, according to the angle formed by the straight line formed by the coordinates (e, f) of the lower left end and the coordinates (e', f') of the lower right end of the license plate and the straight line formed by the lower left end and the lower right end of the standard license plate Adjust in the direction of the straight line where the standard license plate is located; Among them, the generated straight line is calculated through the Euclidean distance. When the license plate is tilted at an angle, the black area presented by the characters will also change accordingly, resulting in the inability to accurately identify the area in the characters. Therefore, it is necessary to adjust the tilt angle of the picture to avoid the decline in the progress of identifying characters.

[0024] When several special characters are detected in the license plate characters, after the central control platform receives the signal, the current detected picture is subjected to grayscale processing. The steps for processing the current several special characters are as follows: Z01: Select similar feature characters in the current license plate, set the same pixel values for length and width in the selected picture, perform grayscale processing on the current character, and calculate the pixel lengths of the abscissa and ordinate of the current character. Compare the lengths between the starting point at the leftmost end of the pixel width and the ending point at the rightmost end of the pixel width of different character endpoints. Characters with the same pixel width are recorded as S1; Calculate the pixel ratio occupied by each character, and judge the similarity according to the pixel ratio. The pixel ratio is , where L x refers to the pixel length occupied by white pixels, and L P refers to the length of the sum of white pixels and black pixels; First judge the differences between different characters through the pixel ratio. For example, when the pixel ratio of the 'S' character is detected to be 65% and the pixel ratio of the 'H' character is 40%, directly skip the judgment of step Z03; Z02: Traverse the pixels of non-license plate characters, and compare the traversal results of non-license plate characters with the traversal results of pixels in the license plate to judge whether the error is within the preset range; Z03: When the result is S1 and the result is within the preset range, traverse the characters with the same pixel width from the leftmost end to the rightmost end of each row and from the uppermost end to the lowermost end of each category in the character pixels until all traversals are completed. Send the different pixel lengths represented by different traversal results to the central control platform for comparison and select the corresponding characters.

[0025] Z04: When it is detected that the error is not within the preset range, traverse the characters in the license plate again until the deviation is within the set range.

[0026] Adjust the character path to 255 using the grayscale value, so that characters with character features are marked as white, and those without character features are marked as black. The actual character pixels are clearer when compared with the pixels taken and modulated by the shooting terminal. Therefore, it is necessary to compare with the pixel length and width represented by the actual characters to judge whether the characters formed by the shooting terminal are within the error range. Among them, the pixel length and width refer to the abscissa and ordinate formed by calculating the number of white grids in each row and each column.

[0027] When it is detected that the similarity between two or more characters in the license plate number exceeds the standard similarity, record the number of times the current vehicle parks in different parking lots, and save the characteristics of the current license plate number and the corresponding vehicle model in the database to facilitate the shooting terminal to quickly identify the license plate number and quickly pass through the curve.

[0028] Embodiment 1: When it is detected that the current license plate number contains the character "B", and it is detected that the similarity between this character and the character "8" is relatively high. Therefore, the image is grayscale processed, and the grayscale is adjusted to 255, so that the white area is the number and the black area is the background of the character. The license plate number characters are set with equal divided areas. The position coordinates of the upper left corner of the current character "B" are set as (x, y) = (50, 50), and the coordinates of the lower right corner are set as (10, 10). The position coordinates of the upper left corner of the "8" in the current character are (a, b) = (50, 50), and the coordinates of the lower right corner are set as (10, 10). The areas of the above characters are judged separately.

[0029] It should be noted that in this article, relational terms such as first and second are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the term "comprising", "including" or any other variant thereof is intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements not only includes those elements, but also includes other elements not expressly listed, or also includes elements inherent to such process, method, article or device.

[0030] Finally, it should be noted that the above are only the preferred embodiments of the present invention and are not used to limit the present invention. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art can still modify the technical solutions described in the foregoing embodiments, or perform equivalent replacements for some of the technical features. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principle of the present invention shall be included within the protection scope of the present invention.

Claims

1. A parking non-contact payment system based on big data, characterized by: The system includes a central control platform, a speed sensor, a distance judgment module, a holographic projection device, an alarm prompt module, a display screen, a special character judgment module, a similarity monitoring module, an image processing module, a character comparison module, a GPRS positioning module, a database and a shooting terminal. The central control platform is used to control the operation process of the entire system and send the received command to the next processing terminal. The speed sensor is installed on both sides of the parking lot curve to detect the speed of the vehicle traveling in the lane. The distance judgment module is used to measure the distance between the two sides of the vehicle tires when the vehicle turns, and judge whether the vehicle license plate number will be scanned according to the offset angle of the current vehicle. The holographic projection device is installed on one side of the shooting terminal to move the route of the vehicle to one side when the vehicle's driving route deviates. The alarm prompt module is used to send an alarm prompt to the central control platform when it is detected that the current vehicle is retreating to the rear. The display screen is used to display the license plate number of the current vehicle to verify whether the license plate number of the current vehicle is consistent with the license plate number displayed on the display screen. The special character judgment module is used to The undetected characters in the license plate number are monitored, and the number of special characters contained in the current characters is identified, and the license plate number is identified using different methods according to the number of special characters. The similarity monitoring module is used to determine the error rate of the current character recognition according to the recognition record stored in the database when it is detected that there is only one special character in the license plate number, and determine the current character recognition result according to the similarity judgment and error rate between the current character and other characters. The image processing module is used to process the picture when it is detected that there are several special characters in the vehicle number, and determine whether the current character matches the pixel length and pixel width of the current character in the picture with the pixel length and pixel width corresponding to different characters. The character comparison module is used to compare the pixel values ​​between similar letters and numbers. The GPRS positioning module is used to locate the position of the vehicle in the curve. The database is used to record and save the data of the vehicle parking in the city. The shooting terminal is used to take pictures of the vehicle and the license plate number, and send the taken pictures to the central control platform for processing, so as to timely understand the status of the current curve.

2. The parking non-contact payment system based on big data according to claim 1 is characterized by: Assume that the exit of the current parking lot is in the shape of a curve. The speed sensor installed on the side of the curve is used to upload the received speed to the central control platform, and the set of speeds of several vehicles is determined to be V={v1,v2,v3...v n }, when the vehicle speed V is detected i >V p When , it means that the current vehicle speed exceeds the normal driving range, where V i Refers to the current vehicle speed, V p Refers to the set speed threshold. When the current vehicle is turning on a curve, the maximum vertical distance between the current vehicle and one side of the curve is set to d. According to the current vehicle tires in different positions W={w1,w2,w3...w n }Rotation angle The curve W is formed, and W=kx+b is set, where k and b are constants of the curve function, and x is the driving time. The central control platform detects that the leftmost position that the camera module can capture is H i , the rightmost position that can be detected is H r , the curve formed is Y=ao 2 +bo+c, where a, b, c refer to the constants of the curve function Y, o refers to the horizontal coordinate, and Y refers to the vertical coordinate. According to the vehicle's driving trajectory and the current vehicle's final stop position W k , determine whether the license plate number of the current vehicle's final stop position is within the curve formed by the shooting module. When the shooting terminal can detect the length from the leftmost end to the rightmost end of the license plate number, it means that the vehicle is driving normally in the curve. When the shooting terminal cannot detect the length from the leftmost end to the rightmost end of the license plate number, the holographic projection device is used to move the roadside line that is longer on one side of the vehicle toward the direction of the vehicle to form a multi-lane driving lane, and the license plate numbers of all vehicles can be recognized.

3. The parking non-contact payment system based on big data according to claim 1 is characterized by: When the vehicle's speed v is detected i >v p When the license plate number detected on the display screen is half of the license plate number characters, the position of the vehicle behind the current vehicle is detected in real time. When it is detected that the position of the current vehicle d and the rear vehicle J is greater than the set distance, the holographic projection device is used to project a path length of R between the front vehicle and the rear vehicle, so that the front vehicle can reverse in time and re-verify the license plate number. When it is detected that the distance between the rear vehicle and the current vehicle is less than the preset distance, the central control module is used to send a signal to the alarm prompt module to prompt the rear vehicle in time.

4. The parking non-contact payment system based on big data according to claim 3 is characterized by: When a vehicle is driving in a curve and detects that the distance between the rear vehicle and the front vehicle is less than the preset distance, the central control platform prompts the rear vehicle. In the two-dimensional plane, the position of the front vehicle before reversing is P=(a,b). When the license plate number information of the front vehicle is not captured, the front vehicle needs to reverse again. At this time, the position of the vehicle within time t is P'=(a2,b2). When the speed e of the front vehicle reversing is detected, i When the speed is greater than the preset speed e, the rear vehicle needs to move in the opposite direction of the front vehicle to prevent the front vehicle from braking and hitting the rear vehicle. When it is detected that the reversing speed of the front vehicle is less than the preset speed, the rear vehicle only needs to move m meters behind the front vehicle, where m refers to the standard distance between the front vehicle and the rear vehicle.

5. A parking non-sensing payment system based on big data according to claim 1 or 3, characterized in that: When it is detected that the license plate characters displayed on the display screen are only half of the license plate number, and there is a special character among the undetected license plate characters, the central control platform sends a signal to the database, and retrieves the number of times the vehicle has parked in all parking lots is Q times, and the number of times the vehicle has been re-scanned by the camera terminal is Q'. When the accuracy of the camera terminal is detected When the accuracy is lower than the standard, the characters in the current license plate are judged, and the current two characters are set as x and y. The photo taken by the image processing module is grayed and binarized, and the position coordinates of the upper left corner of the current character are set as (x, y), and the coordinates of the lower right corner are set as , calculate the area of ​​the black area in the current two characters, calculate and judge whether the area of ​​the black area is the same, where the area difference error rate of the two characters is , select the characters in the license plate according to the area size.

6. The parking non-contact payment system based on big data according to claim 5 is characterized by: When the license plate in the image displayed on the central control platform is tilted, the angle between the straight line formed by the coordinates of the lower left end (e, f) and the lower right end (e', f') of the license plate and the straight line formed by the lower left and right ends of the standard license plate is Adjust in the direction of the straight line where the standard license plate is located.

7. The parking non-contact payment system based on big data according to claim 1 is characterized by: When a number of special characters are detected in the license plate characters, the central control platform receives the signal and performs grayscale processing on the currently detected image. The steps for processing the current number of special characters are as follows: Z01: Select similar characteristic characters in the current license plate, set the same length and width pixel values ​​in the selected picture, perform grayscale processing on the current character, and calculate the pixel length in the horizontal and vertical coordinates of the current character. Compare the lengths between the leftmost starting point of the pixel width and the rightmost end point of the pixel width in different character endpoints, and record the characters with the same length of pixel width as S1; The pixel ratio of each character is calculated, and the similarity is determined based on the pixel ratio. The pixel ratio is , where L x Refers to the pixel length occupied by white pixels, L P It refers to the length of the sum of white pixels and black pixels. The difference between different characters is first determined by the pixel ratio. Z02: Traverse the pixels of non-license plate characters and compare the traversal results of non-license plate characters with the traversal results of pixels in the license plate to determine whether the error is within a preset range; Z03: According to result S1 and when the result is within a preset range, characters with the same pixel width are traversed from the leftmost to the rightmost end of each row of character pixels and from the topmost to the bottommost end of each category until all traversals are completed, and different pixel lengths represented by different traversal results are sent to the central control platform for comparison, and the corresponding character is selected; Z04: When it is detected that the error is not within the preset range, the characters in the license plate are re-traversed until the deviation is within the preset range.

8. The parking non-contact payment system based on big data according to claim 7 is characterized by: When it is detected that the similarity between two or more characters in the license plate number exceeds the standard similarity, the number of times the current vehicle has parked in different parking lots is recorded, and the characteristics of the current license plate number and the corresponding vehicle model are saved in the database, so that the shooting terminal can quickly identify the license plate number and pass the curve quickly.

Images