CN114742558A - Method for detecting parking lot payment two-dimensional code based on vehicle-mounted all-round fisheye camera - Google Patents

Method for detecting parking lot payment two-dimensional code based on vehicle-mounted all-round fisheye camera Download PDF

Info

Publication number
CN114742558A
CN114742558A CN202210457049.4A CN202210457049A CN114742558A CN 114742558 A CN114742558 A CN 114742558A CN 202210457049 A CN202210457049 A CN 202210457049A CN 114742558 A CN114742558 A CN 114742558A
Authority
CN
China
Prior art keywords
fisheye camera
dimensional code
vehicle
view
detection
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.)
Pending
Application number
CN202210457049.4A
Other languages
Chinese (zh)
Inventor
范思源
袁霖
刘富钰
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Chongqing Changan Automobile Co Ltd
Original Assignee
Chongqing Changan Automobile Co Ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Chongqing Changan Automobile Co Ltd filed Critical Chongqing Changan Automobile Co Ltd
Priority to CN202210457049.4A priority Critical patent/CN114742558A/en
Publication of CN114742558A publication Critical patent/CN114742558A/en
Pending legal-status Critical Current

Links

Images

Classifications

    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06QINFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q20/00Payment architectures, schemes or protocols
    • G06Q20/30Payment architectures, schemes or protocols characterised by the use of specific devices or networks
    • G06Q20/32Payment architectures, schemes or protocols characterised by the use of specific devices or networks using wireless devices
    • G06Q20/327Short range or proximity payments by means of M-devices
    • G06Q20/3276Short range or proximity payments by means of M-devices using a pictured code, e.g. barcode or QR-code, being read by the M-device
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06KGRAPHICAL DATA READING; PRESENTATION OF DATA; RECORD CARRIERS; HANDLING RECORD CARRIERS
    • G06K7/00Methods or arrangements for sensing record carriers, e.g. for reading patterns
    • G06K7/10Methods or arrangements for sensing record carriers, e.g. for reading patterns by electromagnetic radiation, e.g. optical sensing; by corpuscular radiation
    • G06K7/14Methods or arrangements for sensing record carriers, e.g. for reading patterns by electromagnetic radiation, e.g. optical sensing; by corpuscular radiation using light without selection of wavelength, e.g. sensing reflected white light
    • G06K7/1404Methods for optical code recognition
    • G06K7/146Methods for optical code recognition the method including quality enhancement steps
    • G06K7/1465Methods for optical code recognition the method including quality enhancement steps using several successive scans of the optical code

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Business, Economics & Management (AREA)
  • General Physics & Mathematics (AREA)
  • Strategic Management (AREA)
  • General Business, Economics & Management (AREA)
  • Accounting & Taxation (AREA)
  • Computer Networks & Wireless Communication (AREA)
  • Quality & Reliability (AREA)
  • Health & Medical Sciences (AREA)
  • Electromagnetism (AREA)
  • General Health & Medical Sciences (AREA)
  • Toxicology (AREA)
  • Artificial Intelligence (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Traffic Control Systems (AREA)

Abstract

The invention discloses a method for detecting a parking lot payment two-dimensional code based on a vehicle-mounted all-round fisheye camera, which comprises the following steps: the method comprises the steps that a look-around fisheye camera is adopted to shoot images of a plurality of parking lot two-dimensional codes in advance, the occurrence areas of the two-dimensional codes in the images shot by the look-around fisheye camera are counted, the positions where the two-dimensional codes frequently appear and can be clearly identified in the images are recorded, and then the positions are split into a plurality of sliding windows; acquiring an image shot by a panoramic fisheye camera in real time, and extracting a picture corresponding to a sliding window in the image; and carrying out distortion correction on the picture corresponding to the sliding window, carrying out two-dimensional code detection on the picture after the distortion correction, stopping the detection of the two-dimensional code if the two-dimensional code is detected, and otherwise, repeating the steps until the two-dimensional code is detected. The method can effectively avoid garage congestion, selectively detect payment two-dimensional code images acquired by the vehicle-mounted all-round-looking fisheye camera, effectively reduce the amount of calculation, improve the number of detection frames, avoid blockage and improve the success rate of identification.

Description

Method for detecting parking lot payment two-dimensional code based on vehicle-mounted all-round fisheye camera
Technical Field
The invention belongs to the technical field of two-dimension code recognition and mobile payment, and particularly relates to a method for detecting a parking lot payment two-dimension code based on a vehicle-mounted all-round fisheye camera.
Background
The automotive industry is undergoing an intelligent revolution. Compared with the traditional automobile design, the current automobile is equipped with a plurality of sensors and high-performance computing platforms so as to meet the increasing intelligent functional requirements. Among them, look around fisheye camera and on-vehicle infotainment terminal controller based on tall and erect platform have become the standard of a large amount of middle and high-end car brands. Look around fisheye camera is used for monitoring the condition around the car usually, provides the image information of driver's vision blind area in parking process, prevents to bump with the barrier emergence accident in the blind area. The vehicle-mounted information entertainment terminal based on the android platform can provide more personalized, intelligent and strong-expansibility information entertainment services for drivers.
Meanwhile, with the progress of computer vision technology and internet technology, many parking lots have provided card-free, cashless, unattended parking services. When a driver drives into the parking lot, a camera at the entrance of the parking lot identifies the license plate and starts timing. When leaving the parking lot, the driver scans the two-dimensional code provided by the parking lot to pay. When the vehicle leaves the parking lot, the license plate is identified by the camera at the exit of the parking lot, the payment condition of the vehicle is confirmed, and if the payment condition is settled, the vehicle is released. This parking management model has greatly optimized the parking experience over the past, but has its shortcomings. One of the conditions is that the position, size and illumination condition of the payment two-dimensional code are different according to the parking lot. The driver needs to look for the two-dimensional code first when collecting fee, opens the cell-phone and sweeps a yard function, stretches out the hand door window, aims at the two-dimensional code and scans, accomplishes on the cell-phone again and collects fee. The operation process is not simple and convenient enough, and the garage is easy to jam due to misoperation.
Disclosure of Invention
Aiming at the defects in the prior art, the invention aims to provide the method for detecting the payment two-dimensional code of the parking lot based on the vehicle-mounted fisheye camera, the method can effectively avoid garage congestion, selectively detects the payment two-dimensional code image obtained by the vehicle-mounted looking-around fisheye camera, effectively reduces the operation amount, improves the number of detection frames, avoids blockage, and improves the success rate of identification.
The technical scheme of the invention is realized as follows:
the method for detecting the parking lot payment two-dimensional code based on the vehicle-mounted all-round fisheye camera comprises the following steps:
s1: the method comprises the steps that a look-around fisheye camera is adopted to shoot images of a plurality of parking lot two-dimensional codes in advance, the occurrence areas of the two-dimensional codes in the images shot by the look-around fisheye camera are counted, the positions where the two-dimensional codes frequently appear and can be clearly identified in the images are recorded, and then the positions are split into a plurality of sliding windows;
s2: acquiring an image shot by a panoramic fisheye camera in real time, and extracting a picture corresponding to a sliding window in the image;
s3: performing distortion correction on the picture corresponding to the sliding window in the S2 to obtain a picture after distortion correction, performing two-dimensional code detection on the picture after distortion correction, stopping performing two-dimensional code detection if the two-dimensional code is detected, and otherwise, entering S4;
s4: and repeating the steps S2-S3 until the two-dimensional code is detected.
Furthermore, the all-round looking fisheye camera comprises a forward looking fisheye camera, a left looking fisheye camera and a right looking fisheye camera.
Further, according to different vehicle speeds V of the vehicle, the following conditions are detected, and the detection is immediately stopped as long as the two-dimensional code is detected in the detection process:
the first condition is as follows: when V =0, the detection functions of the foresight fisheye camera, the left-view fisheye camera and the right-view fisheye camera are started, and at most N times of two-dimensional code detection is respectively carried out through the foresight fisheye camera, the left-view fisheye camera and the right-view fisheye camera.
Case two: when V is more than 0 and less than or equal to 5 Km/h, starting the detection functions of the front-view fisheye camera, the left-view fisheye camera and the right-view fisheye camera, and if the ultrasonic radar displays that no barrier exists in the set ranges in front of the vehicle, on the left side and on the right side, performing two-dimensional code detection for at most M times through the front-view fisheye camera, the left-view fisheye camera and the right-view fisheye camera respectively; if the ultrasonic radar displays that the corresponding sides in the set ranges of the front side, the left side and the right side of the vehicle are provided with the obstacles, the fisheye cameras on the sides with the obstacles perform two-dimensional code detection, and the fisheye cameras on the sides without the obstacles perform two-dimensional code detection for M times at most respectively.
Case three: when V is more than 5 Km/h and less than or equal to 15 Km/h, starting the detection functions of the front-view fisheye camera, the left-view fisheye camera and the right-view fisheye camera, judging whether the steering angle of the vehicle is more than or equal to 30 degrees, and if so, performing two-dimensional code detection through the front-view fisheye camera; if not, the detection function of the front-view fisheye camera is closed, meanwhile, two-dimensional code detection is carried out through the left-view fisheye camera and the right-view fisheye camera, if the ultrasonic radar displays that no obstacle exists in the set range of the left side and the right side of the vehicle, M-time two-dimensional code detection is carried out through the left-view fisheye camera or the right-view fisheye camera at most, if the ultrasonic radar displays that obstacles exist in the corresponding side in the set range of the left side and the right side of the vehicle, two-dimensional code detection is carried out through the fisheye camera on the side of the obstacle, and M-time two-dimensional code detection is carried out through the fisheye camera on the side of the obstacle at most.
Case four: when V is more than 15 Km/h and less than or equal to 25 Km/h, the detection function of the front-view fisheye camera is closed, the detection functions of the left-view fisheye camera and the right-view fisheye camera are opened, if the ultrasonic radar displays that no obstacle exists in the set range of the left side and the right side of the vehicle, the left-view fisheye camera or the right-view fisheye camera carries out two-dimensional code detection for at most M times respectively, if the ultrasonic radar displays that an obstacle exists on the corresponding side in the set range of the left side and the right side of the vehicle, the fisheye camera on the side of the obstacle carries out two-dimensional code detection for at most M times, and the fisheye camera on the side without the obstacle carries out two-dimensional code detection for at most M times respectively.
And a fifth situation: and when the V is more than 25 Km/h, closing the detection functions of the front-view fisheye camera, the left-view fisheye camera and the right-view fisheye camera, and not detecting the two-dimensional code.
Further, in case one, N is less than or equal to 3.
Further, the ultrasonic radar displays that an obstacle is in the front of the vehicle within 3 m, and the two-dimensional code detection is carried out through the front-looking fisheye camera; the ultrasonic radar displays that obstacles exist in the left side and the right side 2 m of the vehicle, and then two-dimensional code detection is carried out through the left-view fisheye camera and the right-view fisheye camera.
Further, M equals 2, adding latency between the two detections.
Further, an image shot by the forward-looking fisheye camera is split into a sliding window positioned on the left side of the image and a sliding window positioned on the right side of the image; the images shot by the left-view fisheye camera and the right-view fisheye camera are split into three sliding windows, wherein the two sliding windows are transversely arranged in parallel to form a transverse sliding window combination, and the other sliding window is positioned below the transverse sliding window combination to form a longitudinal sliding window combination.
Further, in the third case, when the vehicle steering angle is greater than or equal to 30 °, the vehicle turns to the left at the same time, the sliding window on the right side of the image shot by the forward looking fisheye camera is opened, and the sliding window on the left side of the image is closed; when the vehicle turns to the right, the sliding window positioned on the left side of the image shot by the front-looking fisheye camera is opened, and the sliding window positioned on the right side of the image is closed.
Further, when V is more than 5 Km/h and less than or equal to 25 Km/h, images of the left-view fisheye camera and the right-view fisheye camera are obtained for two-dimensional code detection, and transverse sliding window combination and longitudinal sliding window combination are alternately used for two-dimensional code detection.
Compared with the prior art, the invention has the following beneficial effects:
1. according to the invention, the vehicle-mounted all-round fisheye camera is adopted to replace a mobile phone camera, so that the front-looking fisheye camera, the left-looking fisheye camera and the right-looking fisheye camera can continuously acquire payment two-dimensional codes in the environment in the driving process of the vehicle, when a driver needs to pay, the recognized payment two-dimensional codes can be displayed on a screen of a vehicle-mounted information entertainment terminal and are provided for the driver to scan, the driver does not need to stop the vehicle before the two-dimensional codes to complete the whole payment process, and the congestion caused at an exit of a parking lot is avoided.
2. According to the invention, through setting of the detection strategy, the forward-looking fisheye camera, the left-looking fisheye camera and the right-looking fisheye camera are selectively adopted to shoot images, and the sliding window is selectively used, so that the requirement of two-dimensional code detection on the computing capacity is reduced, the detection frame number is also improved, the jamming is avoided, and the identification success rate is improved.
Drawings
FIG. 1-schematic flow chart of the present invention.
Fig. 2-a schematic structural view of a sliding window combination of a right-view fisheye camera and a left-view fisheye camera.
Figure 3-detection strategy of the front-view fisheye camera.
Fig. 4-right view fisheye camera detection strategy.
Fig. 5-left view fisheye camera detection strategy.
Detailed Description
The invention is described in further detail below with reference to the drawings and the detailed description.
The method for detecting the parking lot payment two-dimensional code based on the vehicle-mounted all-round fisheye camera comprises the following steps:
s1: the method comprises the steps that a look-around fisheye camera is adopted to shoot images of a plurality of parking lot two-dimensional codes in advance, the occurrence areas of the two-dimensional codes in the images shot by the look-around fisheye camera are counted, the positions where the two-dimensional codes frequently appear and can be clearly identified in the images are recorded, and then the positions are split into a plurality of sliding windows;
s2: after a vehicle enters a parking lot, acquiring an image shot by a looking-around fisheye camera in real time, and extracting a picture corresponding to a sliding window;
s3: performing distortion correction on the picture corresponding to the sliding window in the S2 to obtain a picture after the distortion correction, performing two-dimensional code detection on the picture after the distortion correction, stopping performing the detection on the two-dimensional code if the two-dimensional code is detected, and otherwise, entering S4;
s4: and repeating the steps S2-S3 until the two-dimensional code is detected.
In specific implementation, the all-round looking fisheye camera comprises a forward looking fisheye camera, a left looking fisheye camera and a right looking fisheye camera.
Like this, on-vehicle looking around the fisheye camera just can replace the cell-phone camera, and at the vehicle driving in-process, the two-dimensional code of paying in the incessant collection environment of forward looking fisheye camera, left side looking fisheye camera and right side looking fisheye camera, when the driver needs to pay, can show the two-dimensional code of paying who discerns on-vehicle information entertainment terminal screen, provide the driver scanning for the driver need not to stop the vehicle and accomplish whole process of paying before the two-dimensional code, thereby avoids causing the jam in parking area exit.
Meanwhile, the field angle of the fisheye camera is about 180 degrees generally, the payment two-dimensional code obtained by shooting has serious barrel distortion, and the two-dimensional code in the image shot by the fisheye camera cannot be identified. Therefore, the image is shot through the all-round looking fisheye camera, then the image is split to obtain the sliding windows, then each sliding window is subjected to distortion correction, then the sliding windows after the distortion correction are identified, and if the sliding windows contain the two-dimensional codes, the two-dimensional codes can be effectively detected.
And obtaining a mapping matrix from the image of the all-round fisheye camera to the distortion-removed image by using the internal reference matrix, the distortion parameters and the virtual internal reference matrix of the all-round fisheye camera. And the distortion-removed image corresponding to each sliding window is transformed by the mapping matrix, and the image after distortion removal is directly obtained from the fisheye image through one-step transformation.
During specific implementation, the following conditions are detected according to different vehicle speeds V of the vehicle, and detection is immediately stopped as long as the two-dimensional code is detected in the detection process:
the first condition is as follows: when V =0, starting the detection functions of the foresight fisheye camera, the left-view fisheye camera and the right-view fisheye camera, and respectively carrying out two-dimensional code detection for at most N times through the foresight fisheye camera, the left-view fisheye camera and the right-view fisheye camera.
Case two: when V is more than 0 and less than or equal to 5 Km/h, starting the detection functions of the front-view fisheye camera, the left-view fisheye camera and the right-view fisheye camera, and if the ultrasonic radar displays that no barrier exists in the set ranges in front of the vehicle, on the left side and on the right side, performing two-dimensional code detection for at most M times through the front-view fisheye camera, the left-view fisheye camera and the right-view fisheye camera; if the ultrasonic radar displays that the corresponding sides in the set ranges of the front, the left side and the right side of the vehicle are provided with obstacles, the fisheye cameras on the sides with the obstacles are used for detecting the two-dimensional codes, and the fisheye cameras on the sides without the obstacles are used for detecting the two-dimensional codes at most for M times.
Therefore, when the corresponding sides in the setting ranges of the front, the left side and the right side of the ultrasonic radar vehicle are provided with obstacles, the obstacles are generally adjacent to a wall or a column, and a two-dimensional code is usually pasted on the obstacles, so that the corresponding fisheye cameras are adopted to detect the two-dimensional code, and when no obstacle exists, the front is open, the two-dimensional code is generally not contained, the two-dimensional code is detected for M times at most, and M in the place can be set as required.
Case three: when V is more than 5 Km/h and less than or equal to 15 Km/h, starting the detection functions of the front-view fisheye camera, the left-view fisheye camera and the right-view fisheye camera, judging whether the steering angle of the vehicle is more than or equal to 30 degrees, and if so, performing two-dimensional code detection through the front-view fisheye camera; if not, the detection function of the front-view fisheye camera is closed, meanwhile, two-dimensional code detection is carried out through the left-view fisheye camera and the right-view fisheye camera, if the ultrasonic radar displays that no obstacle exists in the set range of the left side and the right side of the vehicle, M-time two-dimensional code detection is carried out through the left-view fisheye camera or the right-view fisheye camera at most, if the ultrasonic radar displays that obstacles exist in the corresponding side in the set range of the left side and the right side of the vehicle, two-dimensional code detection is carried out through the fisheye camera on the side of the obstacle, and M-time two-dimensional code detection is carried out through the fisheye camera on the side of the obstacle at most.
Case four: when V is more than 15 Km/h and less than or equal to 25 Km/h, the detection function of the front-view fisheye camera is closed, the detection functions of the left-view fisheye camera and the right-view fisheye camera are opened, if the ultrasonic radar displays that no obstacle exists in the set range of the left side and the right side of the vehicle, the left-view fisheye camera or the right-view fisheye camera carries out two-dimensional code detection for at most M times respectively, if the ultrasonic radar displays that an obstacle exists on the corresponding side in the set range of the left side and the right side of the vehicle, the fisheye camera on the side of the obstacle carries out two-dimensional code detection for at most M times, and the fisheye camera on the side without the obstacle carries out two-dimensional code detection for at most M times respectively.
Case five: and when the V is more than 25 Km/h, closing the detection functions of the front-view fisheye camera, the left-view fisheye camera and the right-view fisheye camera, and not detecting the two-dimensional code.
In the specific implementation, N is less than or equal to 3 in the first case. In the embodiment, when the vehicle is in a stop state, the maximum detection times are set to 3 times, if the two-dimensional code cannot be detected, the two-dimensional code detection is stopped, the vehicle is waited for starting, and the calculation amount of the vehicle-mounted infotainment terminal can be effectively saved.
In specific implementation, the ultrasonic radar displays that an obstacle is in front of the vehicle within 3 m, and the two-dimensional code detection is carried out through the front-looking fisheye camera; the ultrasonic radar displays that obstacles exist in the left side and the right side 2 m of the vehicle, and then two-dimensional code detection is carried out through the left-view fisheye camera and the right-view fisheye camera.
The detection ranges of the front-view fisheye camera, the left-view fisheye camera and the right-view fisheye camera are limited, the setting range of the front-view fisheye camera is 3 m, and the setting range of the left-view fisheye camera and the right-view fisheye camera is 2 m.
In specific implementation, M is equal to 2, and a waiting time is added between two detections.
When the ultrasonic radar does not detect the obstacle, the possibility that the two-dimensional code exists is low, and the waiting time is added, so that the detection frequency can be effectively reduced, and the occupation of the two-dimensional code detection on the computing capacity is reduced.
In specific implementation, an image shot by the front-view fisheye camera is split into a sliding window positioned on the left side of the image and a sliding window positioned on the right side of the image; the images shot by the left-view fisheye camera and the right-view fisheye camera are split into three sliding windows, wherein the two sliding windows are transversely arranged in parallel to form a transverse sliding window combination, and the other sliding window is positioned below the transverse sliding window combination to form a longitudinal sliding window combination.
The structural schematic diagram of the sliding window combination of the right-view fisheye camera and the left-view fisheye camera is shown in fig. 2, in fig. 1, the sliding windows 1 and 2 form a transverse sliding window combination, and the sliding windows 3 form a longitudinal sliding window combination. The purpose of 1 and 2 sliding windows is used for detecting the two-dimensional code with the height of about 1.4-1.8 m on the stand column of the parking lot, and the purpose of 3 sliding windows is used for detecting the two-dimensional code with a short distance or a crossed bottom position.
In a third case, when the steering angle of the vehicle is greater than or equal to 30 degrees, the vehicle turns to the left at the same time, the sliding window on the right side of the image shot by the front-view fisheye camera is opened, and the sliding window on the left side of the image is closed; when the vehicle turns to the right, the sliding window positioned on the left side of the image shot by the front-looking fisheye camera is opened, and the sliding window positioned on the right side of the image is closed.
In specific implementation, when V is more than 5 Km/h and less than or equal to 25 Km/h, images of the left-view fisheye camera and the right-view fisheye camera are obtained to perform two-dimensional code detection, and transverse sliding window combination and longitudinal sliding window combination are alternately used to perform two-dimensional code detection.
When the vehicle speed is higher, the transverse sliding window combination and the longitudinal sliding window combination are alternately used for two-dimensional code detection, so that the detection speed of a single picture can be increased.
Fig. 3 shows the detection strategy of the front-view fisheye camera, in which all sliding windows are combined into a sliding window located on the left side of the image and a sliding window located on the right side of the image. When the vehicle speed is 0, the two-dimensional code detection is only carried out three times, and then the vehicle waits until the vehicle starts. When the vehicle speed is less than or equal to 5 km/h, the sliding window combination of the forward-looking fisheye camera is completely started, but if the ultrasonic radar does not detect an obstacle in a sector area of 3 m ahead, certain waiting time is added between the two detections. The significance of the strategy is that the probability of the two-dimensional code appearing when no obstacle exists in front is low, but the probability of false alarm of the ultrasonic radar is considered, for example, the probability that the ultrasonic radar with a thin pole on a billboard can not be detected exists, while the two-dimensional code can be detected, the detection is still carried out twice, but the waiting time is added, so that the detection frequency can be effectively reduced, and the occupation of the two-dimensional code detection on the computing capacity is reduced. The vehicle speed of more than 5 km/h but not more than 15 km/h generally means that the vehicle is in a normal running state, and the two-dimensional code is less likely to appear in front, and therefore, detection is not generally performed. However, if the vehicle is steered, it indicates that there is a possibility that there is an obstacle ahead, and therefore, the two-dimensional code detection is started when the vehicle steering angle is equal to or greater than 30 °. And meanwhile, the steering direction is judged. If the vehicle turns left, it means that there is a high possibility that the right side of the image is closer to the obstacle and there is a high possibility that the two-dimensional code appears, and therefore the detection is performed using the sliding window located on the right side of the image. The same applies when the vehicle turns to the right. When the vehicle speed is more than 15 km/h, the possibility that an obstacle stuck with the two-dimensional code appears in front is low, so that the front two-dimensional code detection is closed at the moment.
Fig. 4 shows a detection strategy of a right-view fisheye camera, in which all sliding window combinations are a transverse sliding window combination and a longitudinal sliding window combination. When the vehicle speed is 0 km/h, the detection strategy is the same as that of the forward-looking fisheye camera. When the vehicle speed is less than or equal to 5 km/h, the detection strategy is the same as that of the forward-looking fisheye camera when the vehicle speed is less than or equal to 5 km/h, but the threshold value of the distance between the obstacles is 2 m. When the vehicle speed is more than 5 km/h but less than or equal to 25 km/h, the two sliding window subsets are alternately used for detection. And when the vehicle speed is more than 25 km/h, closing the detection function of the right-view fisheye camera.
Fig. 5 shows a detection strategy of a left-view fisheye camera, in which all sliding window combinations are a transverse sliding window combination and a longitudinal sliding window combination. When the vehicle speed is less than or equal to 15 km/h, the detection strategy is the same as that of a right-view fisheye camera. When the vehicle speed is greater than 15 km/h but less than or equal to 25 km/h, the vehicle is generally in a normal running state. The parking area generally sets up two-way two lanes, and vehicle right side is current under the normal driving state, and the fish eye camera on the left side is too far away from the two-dimensional code, can't detect the two-dimensional code under the general condition, consequently when using aforementioned two sliding window subsets in turn to detect, adds the wait between twice detection, with calculation resource allocation to the fish eye camera of looking right, improves the detection frame number of the fish eye camera of looking right. And when the vehicle speed is more than 25 km/h, closing the detection function of the left-view fisheye camera.
Finally, it should be noted that the above examples of the present invention are only for illustrating the present invention and are not intended to limit the embodiments of the present invention. Variations and modifications in other variations will occur to those skilled in the art upon reading the foregoing description. Not all embodiments are exhaustive. All obvious changes and modifications of the present invention are within the scope of the present invention.

Claims (9)

1. The method for detecting the parking lot payment two-dimensional code based on the vehicle-mounted all-round fisheye camera is characterized by comprising the following steps of:
s1: the method comprises the steps that a look-around fisheye camera is adopted to shoot images of a plurality of parking lot two-dimensional codes in advance, the occurrence areas of the two-dimensional codes in the images shot by the look-around fisheye camera are counted, the positions where the two-dimensional codes frequently appear and can be clearly identified in the images are recorded, and then the positions are split into a plurality of sliding windows;
s2: acquiring an image shot by a looking-around fisheye camera in real time, and extracting a picture corresponding to a sliding window in the image;
s3: performing distortion correction on the picture corresponding to the sliding window in the S2 to obtain a picture after the distortion correction, performing two-dimensional code detection on the picture after the distortion correction, stopping performing the detection on the two-dimensional code if the two-dimensional code is detected, and otherwise, entering S4;
s4: and repeating the steps S2-S3 until the two-dimensional code is detected.
2. The method for detecting the parking lot payment two-dimensional code based on the vehicle-mounted all-round fisheye camera is characterized in that the all-round fisheye camera comprises a front-view fisheye camera, a left-view fisheye camera and a right-view fisheye camera.
3. The method for detecting the parking lot payment two-dimensional code based on the vehicle-mounted all-round fisheye camera is characterized in that detection is carried out according to different vehicle speeds V of the vehicle under the following conditions, and detection is immediately stopped as long as the two-dimensional code is detected in the detection process:
the first condition is as follows: when V =0, starting the detection functions of the front-view fisheye camera, the left-view fisheye camera and the right-view fisheye camera, and respectively performing two-dimensional code detection for at most N times through the front-view fisheye camera, the left-view fisheye camera and the right-view fisheye camera;
case two: when V is more than 0 and less than or equal to 5 Km/h, starting the detection functions of the front-view fisheye camera, the left-view fisheye camera and the right-view fisheye camera, and if the ultrasonic radar displays that no barrier exists in the set ranges in front of the vehicle, on the left side and on the right side, performing two-dimensional code detection for at most M times through the front-view fisheye camera, the left-view fisheye camera and the right-view fisheye camera respectively; if the ultrasonic radar displays that obstacles exist on the corresponding sides in the set ranges of the front, the left side and the right side of the vehicle, carrying out two-dimensional code detection through fisheye cameras on the sides with the obstacles, and respectively carrying out two-dimensional code detection for M times at most by fisheye cameras on the sides without the obstacles;
case three: when V is more than 5 Km/h and less than or equal to 15 Km/h, starting the detection functions of the front-view fisheye camera, the left-view fisheye camera and the right-view fisheye camera, judging whether the steering angle of the vehicle is more than or equal to 30 degrees, and if so, performing two-dimensional code detection through the front-view fisheye camera; if not, the detection function of the front-view fisheye camera is closed, meanwhile, two-dimensional code detection is carried out through the left-view fisheye camera and the right-view fisheye camera, if the ultrasonic radar displays that no obstacle exists in the set range of the left side and the right side of the vehicle, M-time two-dimensional code detection is carried out through the left-view fisheye camera or the right-view fisheye camera at most respectively, if the ultrasonic radar displays that obstacles exist on the corresponding side in the set range of the left side and the right side of the vehicle, two-dimensional code detection is carried out through the fisheye camera on the side of the obstacle, and M-time two-dimensional code detection is carried out through the fisheye camera on the side without the obstacle at most respectively;
case four: when V is more than 15 Km/h and less than or equal to 25 Km/h, closing the detection function of the front-view fisheye camera, and opening the detection functions of the left-view fisheye camera and the right-view fisheye camera, if the ultrasonic radar displays that no obstacle exists in the set range of the left side and the right side of the vehicle, performing two-dimensional code detection at most for M times through the left-view fisheye camera or the right-view fisheye camera, if the ultrasonic radar displays that an obstacle exists on the corresponding side in the set range of the left side and the right side of the vehicle, performing two-dimensional code detection through the fisheye camera on the side with the obstacle, and performing two-dimensional code detection at most for M times through the fisheye camera on the side without the obstacle;
case five: and when the V is more than 25 Km/h, closing the detection functions of the front-view fisheye camera, the left-view fisheye camera and the right-view fisheye camera, and not detecting the two-dimensional code.
4. The method for detecting the parking lot payment two-dimensional code based on the vehicle-mounted all-round fisheye camera as claimed in claim 3, wherein N is less than or equal to 3 in the first case.
5. The method for detecting the parking lot payment two-dimensional code based on the vehicle-mounted all-round fisheye camera as claimed in claim 3, wherein if the ultrasonic radar displays that an obstacle is in the front of the vehicle within 3 m, the two-dimensional code detection is carried out through the all-round fisheye camera; the ultrasonic radar displays that obstacles exist in the left side and the right side 2 m of the vehicle, and then two-dimensional code detection is carried out through the left-view fisheye camera and the right-view fisheye camera.
6. The method for detecting the parking lot payment two-dimensional code based on the vehicle-mounted all-round fisheye camera is characterized in that M is equal to 2, and waiting time is added between two detections.
7. The method for detecting the parking lot payment two-dimensional code based on the vehicle-mounted all-round fisheye camera is characterized in that an image shot by the all-round fisheye camera is split into a sliding window positioned on the left side of the image and a sliding window positioned on the right side of the image; the images shot by the left-view fisheye camera and the right-view fisheye camera are split into three sliding windows, wherein the two sliding windows are transversely arranged in parallel to form a transverse sliding window combination, and the other sliding window is positioned below the transverse sliding window combination to form a longitudinal sliding window combination.
8. The method for detecting the parking lot payment two-dimensional code based on the vehicle-mounted all-round fisheye camera of claim 7 is characterized in that in the third case, when the vehicle steering angle is greater than or equal to 30 degrees, the vehicle turns to the left at the same time, a sliding window on the right side of the image shot by the all-round fisheye camera is opened, and a sliding window on the left side of the image is closed; when the vehicle turns to the right, the sliding window positioned on the left side of the image shot by the front-looking fisheye camera is opened, and the sliding window positioned on the right side of the image is closed.
9. The method for detecting the parking lot payment two-dimensional code based on the vehicle-mounted all-round fisheye camera is characterized in that when V is more than 5 Km/h and less than or equal to 25 Km/h, images of the left-view fisheye camera and the right-view fisheye camera are obtained for two-dimensional code detection, and transverse sliding window combination and longitudinal sliding window combination are alternately used for two-dimensional code detection.
CN202210457049.4A 2022-04-27 2022-04-27 Method for detecting parking lot payment two-dimensional code based on vehicle-mounted all-round fisheye camera Pending CN114742558A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202210457049.4A CN114742558A (en) 2022-04-27 2022-04-27 Method for detecting parking lot payment two-dimensional code based on vehicle-mounted all-round fisheye camera

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202210457049.4A CN114742558A (en) 2022-04-27 2022-04-27 Method for detecting parking lot payment two-dimensional code based on vehicle-mounted all-round fisheye camera

Publications (1)

Publication Number Publication Date
CN114742558A true CN114742558A (en) 2022-07-12

Family

ID=82282840

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202210457049.4A Pending CN114742558A (en) 2022-04-27 2022-04-27 Method for detecting parking lot payment two-dimensional code based on vehicle-mounted all-round fisheye camera

Country Status (1)

Country Link
CN (1) CN114742558A (en)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN115465225A (en) * 2022-08-12 2022-12-13 重庆长安汽车股份有限公司 Service life prolonging method and device of vehicle-mounted camera, vehicle and storage medium

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN115465225A (en) * 2022-08-12 2022-12-13 重庆长安汽车股份有限公司 Service life prolonging method and device of vehicle-mounted camera, vehicle and storage medium
CN115465225B (en) * 2022-08-12 2024-05-10 重庆长安汽车股份有限公司 Service life extension method and device of vehicle-mounted camera, vehicle and storage medium

Similar Documents

Publication Publication Date Title
CN112329552B (en) Obstacle detection method and device based on automobile
CN108482367B (en) Method, device and system for assisting driving based on intelligent rearview mirror
CN106794807B (en) Vehicle-mounted vidicon control device
CN112581641A (en) Vehicle charging method, storage medium, and electronic device
CN114742558A (en) Method for detecting parking lot payment two-dimensional code based on vehicle-mounted all-round fisheye camera
CN110264781A (en) A kind of intelligent parking lot charging administration system
CN112937445B (en) 360-degree vehicle safety auxiliary method and vehicle-mounted system
CN208789581U (en) Multifunctional driving auxiliary device
CN104157134A (en) Real-time on-line dead-zone-free street scene sharing system for vehicles
CN110667571A (en) Automatic parking control system interacting with parking lot
CN110949256A (en) Auxiliary parking device and method for motor vehicle
CN110053627A (en) Driving evaluation system and storage medium
CN113033479A (en) Multi-layer perception-based berthing event identification method and system
CN114407928A (en) Vehicle avoidance control method and vehicle avoidance control device
CN112926404B (en) Active interactive human-vehicle passing system and method
CN111959417B (en) Automobile panoramic image display control method, device, equipment and storage medium
CN114750747B (en) Automatic identification parking method and system capable of being matched with different man-machine parameters
CN116246251A (en) Vehicle bottom safety detection method and system
CN214796205U (en) 360-degree panoramic wireless safety auxiliary system for rear loading of motor vehicle
CN115303263A (en) Automatic parking method and system based on neural network
CN114049794A (en) Vehicle-mounted safety auxiliary driving system based on smart phone
CN211280989U (en) Automatic parking control system interacting with parking lot
CN109849795B (en) Method and system for controlling turning of rearview mirror
CN111612925A (en) Parking space management method, server and parking management system
KR20210035360A (en) License Plate Recognition Method and Apparatus for roads

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