CN109543613A - Vehicle Speed and Vehicle License Plate Recognition System and method based on TOF imaging - Google Patents
Vehicle Speed and Vehicle License Plate Recognition System and method based on TOF imaging Download PDFInfo
- Publication number
- CN109543613A CN109543613A CN201811401087.8A CN201811401087A CN109543613A CN 109543613 A CN109543613 A CN 109543613A CN 201811401087 A CN201811401087 A CN 201811401087A CN 109543613 A CN109543613 A CN 109543613A
- Authority
- CN
- China
- Prior art keywords
- image
- license plate
- character
- processing computer
- image processing
- 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
Links
- 238000000034 method Methods 0.000 title claims abstract description 86
- 238000003384 imaging method Methods 0.000 title claims abstract description 38
- 230000008569 process Effects 0.000 claims abstract description 32
- 230000005540 biological transmission Effects 0.000 claims abstract description 8
- 238000012545 processing Methods 0.000 claims description 139
- 238000010606 normalization Methods 0.000 claims description 21
- 239000013598 vector Substances 0.000 claims description 20
- 230000011218 segmentation Effects 0.000 claims description 16
- 230000004044 response Effects 0.000 claims description 12
- 238000004364 calculation method Methods 0.000 claims description 10
- 238000007781 pre-processing Methods 0.000 claims description 10
- 238000006073 displacement reaction Methods 0.000 claims description 9
- 238000001514 detection method Methods 0.000 claims description 8
- 238000005259 measurement Methods 0.000 claims description 8
- 238000012544 monitoring process Methods 0.000 claims description 7
- 238000009499 grossing Methods 0.000 claims description 6
- 238000005520 cutting process Methods 0.000 claims description 4
- 238000004891 communication Methods 0.000 claims description 3
- 230000007797 corrosion Effects 0.000 claims description 3
- 238000005260 corrosion Methods 0.000 claims description 3
- 238000001914 filtration Methods 0.000 claims description 3
- 239000011159 matrix material Substances 0.000 claims description 3
- 238000012216 screening Methods 0.000 claims description 3
- 230000015572 biosynthetic process Effects 0.000 claims description 2
- 238000009434 installation Methods 0.000 abstract description 8
- 238000012423 maintenance Methods 0.000 abstract description 4
- 238000012806 monitoring device Methods 0.000 abstract description 4
- 206010039203 Road traffic accident Diseases 0.000 abstract description 3
- 238000010586 diagram Methods 0.000 description 9
- 230000006870 function Effects 0.000 description 9
- 230000008901 benefit Effects 0.000 description 7
- 238000004590 computer program Methods 0.000 description 7
- 238000005286 illumination Methods 0.000 description 6
- 238000004422 calculation algorithm Methods 0.000 description 3
- 230000007547 defect Effects 0.000 description 3
- 238000003860 storage Methods 0.000 description 3
- 239000013589 supplement Substances 0.000 description 3
- 230000008859 change Effects 0.000 description 2
- 238000003708 edge detection Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000001052 transient effect Effects 0.000 description 2
- 238000013519 translation Methods 0.000 description 2
- 230000000007 visual effect Effects 0.000 description 2
- 206010047571 Visual impairment Diseases 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 239000000428 dust Substances 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000005484 gravity Effects 0.000 description 1
- 230000006698 induction Effects 0.000 description 1
- 230000005764 inhibitory process Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 239000000779 smoke Substances 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/50—Context or environment of the image
- G06V20/56—Context or environment of the image exterior to a vehicle by using sensors mounted on the vehicle
- G06V20/58—Recognition of moving objects or obstacles, e.g. vehicles or pedestrians; Recognition of traffic objects, e.g. traffic signs, traffic lights or roads
- G06V20/584—Recognition of moving objects or obstacles, e.g. vehicles or pedestrians; Recognition of traffic objects, e.g. traffic signs, traffic lights or roads of vehicle lights or traffic lights
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/24—Aligning, centring, orientation detection or correction of the image
- G06V10/245—Aligning, centring, orientation detection or correction of the image by locating a pattern; Special marks for positioning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/44—Local feature extraction by analysis of parts of the pattern, e.g. by detecting edges, contours, loops, corners, strokes or intersections; Connectivity analysis, e.g. of connected components
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V30/00—Character recognition; Recognising digital ink; Document-oriented image-based pattern recognition
- G06V30/10—Character recognition
- G06V30/14—Image acquisition
- G06V30/148—Segmentation of character regions
- G06V30/153—Segmentation of character regions using recognition of characters or words
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/01—Detecting movement of traffic to be counted or controlled
- G08G1/017—Detecting movement of traffic to be counted or controlled identifying vehicles
- G08G1/0175—Detecting movement of traffic to be counted or controlled identifying vehicles by photographing vehicles, e.g. when violating traffic rules
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/01—Detecting movement of traffic to be counted or controlled
- G08G1/052—Detecting movement of traffic to be counted or controlled with provision for determining speed or overspeed
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/60—Type of objects
- G06V20/62—Text, e.g. of license plates, overlay texts or captions on TV images
- G06V20/625—License plates
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Traffic Control Systems (AREA)
Abstract
The invention discloses a kind of Vehicle Speed based on TOF imaging and Vehicle License Plate Recognition Systems and method, and system includes monitoring device mounting rack and TOF camera, and the pattern process computer of monitoring center is arranged in；Monitoring device mounting rack includes column and is fixedly connected on the mounting rod at the top of column and with uprights vertical setting, and TOF camera is mounted at the top of mounting rod；Vehicle Speed method is comprising steps of step A1, video acquisition and transmission, and step A2, Vehicle Speed identifies；Licence plate recognition method is comprising steps of step B1, video acquisition and transmission, step B2, Car license recognition.Cost of implementation of the invention is low, system is convenient for installation and maintenance, Vehicle Speed accuracy of identification is high, Car license recognition precision is high, road traffic can effectively be managed, traffic accident is reduced, visible light light filling when carrying out vehicle speed measuring and Car license recognition using visible light is avoided and causes light pollution and security risk.
Description
Technical Field
The invention belongs to the technical field of video detection, and particularly relates to a system and a method for identifying the running speed and the license plate of a vehicle based on TOF imaging.
Background
In the modern society, an intelligent traffic system is a development trend of road traffic. The continuously developed and improved visual intelligent traffic monitoring system lays a good foundation for the practical application of the management system of the vehicle road transportation infrastructure. In recent years, the intelligent traffic industry in China is rapidly developed, and a vehicle identification system is widely applied to off-site law enforcement in cities as an important component of intelligent traffic, but the conventional vehicle identification system has many problems, is based on an LED light supplement system, realizes an automatic photographing function by adopting a mode of linkage of a digital camera and a ground induction coil, and is mature in application and relatively stable. However, the conventional identification system has the defects that: the cost is high, the installation and maintenance are inconvenient, and potential safety hazards exist in visible light. For example: the Hangzhou city traffic police squad is proposed in 2015, the light supplement of the existing system frequency reflector lamp can cause urban light pollution, and transient visual obstruction and traffic hidden danger are easily caused to drivers; poor imaging quality and the like under the condition of low illumination in foggy days. In view of the above, the TOF is a technology using near-infrared light three-dimensional imaging, and by using the advantages of clear target detail expression, strong target identification capability, capability of realizing covert active imaging, strong adaptability to haze weather conditions and dust and smoke application environments, and the like, the application of the TOF three-dimensional imaging technology in a vehicle identification system is researched, so that the TOF imaging-based vehicle intelligent identification system is very practical.
Disclosure of Invention
The technical problem to be solved by the invention is to provide a vehicle running speed and license plate recognition system based on TOF imaging, which has the advantages of simple structure, low implementation cost and convenient installation and maintenance, aiming at the defects in the prior art.
In order to solve the technical problems, the invention adopts the technical scheme that: a TOF imaging-based vehicle running speed and license plate recognition system comprises a monitoring equipment mounting rack, a TOF camera and an image processing computer, wherein the monitoring equipment mounting rack and the TOF camera are mounted on one side of a road, and the image processing computer is arranged in a monitoring center and is connected and communicated with the TOF camera through a communication network; the supervisory equipment mounting bracket includes stand and fixed connection at the stand top and with the perpendicular installation pole that sets up of stand, the TOF camera is installed at installation pole top.
Foretell vehicle speed and license plate identification system of traveling based on TOF formation of image, the supervisory equipment mounting bracket is still including setting up the weather shield in TOF camera top, the one end of weather shield is through first bracing piece fixed connection at installation pole top, the other end of weather shield passes through second bracing piece fixed connection at installation pole top.
The invention also provides a TOF imaging-based vehicle running speed identification method which is simple in method step, convenient to implement and high in vehicle running speed identification precision, and the method comprises the following steps:
step A1, video acquisition and transmission: when the vehicle to be identified runs through an imaging area of the TOF camera, the TOF camera shoots a plurality of frames of vehicle images and transmits shot vehicle image signals to the image processing computer in real time;
step A2, vehicle running speed identification: and the image processing computer calls a vehicle running speed calculation module to process the multi-frame vehicle image shot by the TOF camera, and the vehicle running speed is calculated.
In the method, the image processing computer calls the vehicle running speed calculation module in step a2 to process the multiple frames of vehicle images shot by the TOF camera, and the specific process of calculating the vehicle running speed is as follows:
step A201, the image processing computer sets an imaging area of a TOF camera as a speed measuring area;
step A202, the image processing computer detects a plurality of Harris angular points in a first frame image and a plurality of Harris angular points in a last frame image in a speed measurement area;
step A203, the image processing computer calls a feature matching module to extract a feature set of a first frame image and a feature set of a last frame image, and the feature set of the first frame image is matched and corresponds to the feature set of the last frame image to generate a group of matching feature pair sets;
step A204, the image processing computer calls an angular point matching module according to the matching feature pair set, performs angular point matching on a plurality of Harris angular points in the first frame image and a plurality of Harris angular points in the last frame image by adopting a normalized cross-correlation coefficient method, and finds out one-to-one correspondence between the plurality of Harris angular points in the first frame image and the plurality of Harris angular points in the last frame image;
step a205, the image processing computer calculates one-to-one corresponding displacement values between multiple Harris corners in the first frame image and multiple Harris corners in the last frame image, and calculates total displacement d of all Harris cornersTThen according to the formulaCalculating to obtain the position average value d of all Harris angular pointsA(ii) a Wherein, the corner (x) in the first frame image1,y1) And corner (x) in the last frame image1,y1) Corresponding corner point (x)2,y2) Corresponding displacement value d betweenrIs calculated by the formulaN is the total number of Harris angular points which have one-to-one correspondence relation with the last frame image in the first frame image, and the value of N is a positive integer;
step A206, the image processing computer according to the formulaAnd calculating to obtain the vehicle running speed per hour v, wherein D is the actual vehicle running distance corresponding to the imaging area of the TOF camera, gamma is the number of frames of the movement of the last frame image relative to the first frame image, and η is the frame rate.
In the method, when the image processing computer detects multiple Harris corner points in the first frame image and multiple Harris corner points in the last frame image in the velocity measurement area in step a202, the process of detecting the multiple Harris corner points in the image I (x, y) is as follows:
step A2021, image processing computer according to formulaCalculating the gradient I of the image I (x, y) in the direction of the x-axisxAccording to the formulaCalculating the gradient I of the image I (x, y) in the y-axis directiony；
Step 2022, the image processing computer calculates the correlation matrix at each pixelWherein ω (x, y) is a weighting function;
step a2023, the image processing computer sets (ab-c) the formula R to2)-λ(a+b)2Calculating a corner response value R of each pixel point; wherein lambda is an empirical constant and has a value range of 0.04-0.06;
step a2024, the image processing computer searches for a maximum point of the corner response value in the M × M square range at the middle position on the image I (x, y), defines the found maximum point of the corner response value as a threshold, and determines a pixel point as a Harris corner when the corner response value R of the pixel point is greater than the threshold.
The invention also provides a TOF imaging-based vehicle license plate recognition method which is simple in method steps, convenient to implement and high in license plate recognition accuracy, and comprises the following steps:
step B1, video acquisition and transmission: when the vehicle to be identified runs through an imaging area of the TOF camera, the TOF camera shoots a plurality of frames of vehicle images and transmits shot vehicle image signals to the image processing computer in real time;
step B2, license plate recognition: and the image processing computer calls a license plate recognition module to process the multi-frame vehicle images shot by the TOF cameras, and license plate characters are obtained through recognition.
In the method, the image processing computer calls the license plate recognition module in step B2 to process the multiframe vehicle images shot by the plurality of TOF cameras, and the specific process of recognizing and obtaining the license plate characters is as follows:
step B201, vehicle image preprocessing: the image processing computer calls a vehicle image preprocessing module to preprocess the vehicle image and segment the license plate image from the original image;
step B202, license plate recognition pretreatment: the image processing computer calls a license plate processing module before license plate recognition to sequentially perform gray level, binarization, mean value filtering and corrosion processing on the license plate image, and noise interference in the license plate image is filtered;
step B203, license plate character segmentation and recognition: and the image processing computer calls a license plate character segmentation and recognition module to segment and recognize license plate characters to obtain a license plate number.
In the method, in step B201, the image processing computer calls a vehicle image preprocessing module to preprocess the vehicle image, and a specific process of segmenting the license plate image from the original image is as follows:
step B2011, gray level processing: the image processing computer respectively performs gray level processing on a plurality of frames of vehicle images to generate a gray level histogram;
step B2012, edge operator detection: the image processing computer adopts a Sobel operator to carry out edge operator detection processing on the image preprocessed in the step B2011;
step B2013, edge contour rounding treatment: the image processing computer calls an edge contour smoothing module to perform edge contour smoothing on the image processed in the step B2012;
step B2014, license plate positioning and cutting: and B, the image processing computer calls a license plate positioning module to perform license plate positioning on the image processed in the step B2013, determines a license plate area, and segments the license plate image from the original image.
In the method, in step B203, the image processing computer invokes the license plate character segmentation and recognition module to segment and recognize the license plate characters, and the specific process of obtaining the license plate number is as follows:
step B2031, removing frames: the image processing computer calls a frame removing processing module and removes the horizontal frame of the license plate image by adopting a horizontal projection method;
step B2032, license plate character segmentation: the image processing computer calls a license plate character segmentation module and segments license plate characters by combining a horizontal projection method and a vertical projection method;
step B2033, character normalization processing: the image processing computer calls a character normalization processing module and calculates a character normalization value according to a formulaCarrying out normalization processing on the segmented license plate characters to obtain normalized license plate characters; wherein,in order to be able to normalize the character image before it,as the abscissa of the character image before normalization,has a value range ofHoldIn order to normalize the height of the character before it,is the ordinate of the character image before normalization,has a value range ofWoldThe character width before normalization;in order to be the normalized character image,as the abscissa of the normalized character image,has a value range ofHnewIn order to obtain the normalized height of the character,is the ordinate of the normalized character image,has a value range ofWnewThe normalized character width;
step B2034, license plate character recognition: and the image processing computer calls a license plate character recognition module and recognizes the license plate characters by adopting a template matching method.
In the method, when the license plate character recognition module is called by the image processing computer in the step B2034 and the license plate characters are recognized by adopting a template matching method, the specific process of establishing the template library is that each picture of each type of image is averagely divided into 8 parts, each picture area is scanned point by point, the pixel information of the image is recorded and stored in a one-dimensional vector form, and each character picture is provided with a template formed by corresponding 8-dimensional vectors; equally dividing the license plate character image to be recognized into 8 parts, scanning each picture region point by point, recording and storing pixel information of the image in a one-dimensional vector form, determining 8-dimensional vector values of each character image, solving the 8-dimensional vector values of the characters and n-dimensional Euclidean space distances of the 8-dimensional vector values of all template character pictures, storing the 5 template character pictures with the minimum distance, and screening out possible solutions; then, setting a sum variable sum, comparing the character picture to be recognized with the 5 template character pictures stored before one by one, adding 1 to the same sum value, wherein the category of the template character picture with the largest sum value is the category of the character to be recognized, storing the category of the character to be recognized, and finally outputting the stored categories of the character pictures to be recognized of the whole license plate one by one in sequence to finish the character recognition of the whole license plate; wherein the value of n is a positive integer.
Compared with the prior art, the invention has the following advantages:
1. the TOF imaging-based vehicle running speed and license plate recognition system is simple in structure, low in implementation cost and convenient to install and maintain.
2. According to the method for identifying the vehicle running speed based on the TOF imaging, complex and expensive hardware is not needed, the speed is measured only by using the video information acquired by the TOF camera, the TOF camera is convenient to install and maintain, the video image acquired by the TOF camera is processed by an image processing computer, the vehicle running speed can be obtained, the method is not influenced by foggy days, low illumination and the like, and the vehicle running speed identification precision is high.
3. According to the vehicle license plate identification method based on TOF imaging, complex and expensive hardware is not needed, only the TOF camera is used for collecting video information to measure the speed, the TOF camera is convenient to install and maintain, the TOF camera is used for collecting the video image, the TOF camera is used for processing the video image through the image processing computer, license plate information can be obtained, the influence of foggy days, low illumination and the like is avoided, and license plate identification precision is high.
4. The invention utilizes the TOF camera to image, the signal light source adopted by the TOF camera is near infrared light with the central wavelength of 850nm, and infrared light radiated outwards by the vehicle is far infrared light with the central wavelength of 9350nm, thereby avoiding the interference of other light sources on the imaging.
5. When the method is popularized and used, the cost and budget are not excessively increased, the speed measurement precision is further improved, the license plate detection is combined to carry out license plate snapshot recognition on the overspeed illegal vehicle, road traffic can be effectively controlled, traffic accidents are reduced, light pollution caused by license plate snapshot through visible light supplement and potential safety hazards caused by transient visual disturbance to a driver are avoided, and good economic and social benefits are achieved.
In conclusion, the system has the advantages of low implementation cost, convenience in system installation and maintenance, high accuracy in vehicle running speed identification and high accuracy in license plate identification, can effectively manage and control road traffic, reduces traffic accidents, avoids light pollution and potential safety hazards caused by visible light supplementary lighting when the vehicle speed measurement and the license plate identification are carried out by adopting visible light, and has good economic and social benefits.
The technical solution of the present invention is further described in detail by the accompanying drawings and embodiments.
Drawings
Fig. 1 is a schematic structural diagram of a vehicle driving speed and license plate recognition system based on TOF imaging.
FIG. 2 is a flow chart of a method of identifying a vehicle driving speed based on TOF imaging according to the present invention.
FIG. 3 is a flow chart of a method of identifying a license plate of a vehicle based on TOF imaging according to the present invention. Description of reference numerals:
1-TOF camera; 2-an image processing computer; 3-1-column;
3-2-mounting a rod; 3-rain shield; 3-4-a first support bar;
3-5-second support bar.
Detailed Description
As shown in fig. 1, the TOF imaging-based vehicle driving speed and license plate recognition system of the present invention includes a monitoring device mounting rack and a TOF camera 1 installed on one side of a road, and an image processing computer 2 disposed in a monitoring center and connected and communicated with the TOF camera 1 through a communication network; the monitoring equipment mounting frame comprises a vertical column 3-1 and a mounting rod 3-2 which is fixedly connected to the top of the vertical column 3-1 and perpendicular to the vertical column 3-1, and the TOF camera 1 is mounted on the top of the mounting rod 3-2.
In this embodiment, as shown in fig. 1, the monitoring device mounting rack further includes a rain baffle 3-3 disposed above the TOF camera 1, one end of the rain baffle 3-3 is fixedly connected to the top of the mounting rod 3-2 through a first support rod 3-4, and the other end of the rain baffle 3-3 is fixedly connected to the top of the mounting rod 3-2 through a second support rod 3-5.
As shown in fig. 2, the method for identifying the running speed of a vehicle based on TOF imaging of the invention comprises the following steps:
step A1, video acquisition and transmission: when a vehicle to be identified runs through an imaging area of the TOF camera 1, the TOF camera 1 shoots a plurality of frames of vehicle images and transmits shot multi-frame vehicle image signals to the image processing computer 2 in real time;
step A2, vehicle running speed identification: and the image processing computer 2 calls a vehicle running speed calculation module to process the multi-frame vehicle image shot by the TOF camera 1, and the vehicle running speed is calculated.
In the step a2, the image processing computer 2 calls a vehicle running speed calculation module to process the multiple frames of vehicle images shot by the TOF camera 1, and the specific process of calculating the vehicle running speed is as follows:
step A201, the image processing computer 2 sets an imaging area of the TOF camera 1 as a speed measuring area;
step A202, the image processing computer 2 detects multiple Harris angular points in a first frame image and multiple Harris angular points in a last frame image in a speed measurement area;
in this embodiment, when the image processing computer 2 detects multiple Harris corner points in the first frame image and multiple Harris corner points in the last frame image in the velocity measurement area in step a202, the process of detecting the multiple Harris corner points in the image I (x, y) is as follows:
step A2021, the image processing computer 2 according to the formulaCalculating the gradient I of the image I (x) y in the direction of the x-axisxAccording to the formulaCalculating the gradient I of the image I (x, y) in the y-axis directiony；
Step 2022, the image processing computer 2 calculates the correlation matrix at each pixelWherein ω (x, y) is a weighting function;
in specific implementation, the weighting function ω (x, y) is a gaussian function;
step a2023, the image processing computer 2 sets (ab-c) the formula R to2)-λ(a+b)2Calculating the corner response of each pixelA value R; wherein lambda is an empirical constant and has a value range of 0.04-0.06;
step a2024, the image processing computer 2 searches for a maximum point of the corner response value in the M × M square range at the middle position on the image I (x, y), defines the found maximum point of the corner response value as a threshold, and determines a pixel point as a Harris corner when the corner response value R of the pixel point is greater than the threshold.
In particular, M is a positive number less than half the width of the image I (x, y).
Step A203, the image processing computer 2 calls a feature matching module to extract a feature set of a first frame image and a feature set of a last frame image, and matches and corresponds the feature set of the first frame image and the feature set of the last frame image to generate a group of matching feature pair sets;
in specific implementation, for images with different characteristics, characteristics which are easy to extract and can represent the similarity of the images to be matched to a certain extent in the images are selected as matching bases, so that the defect of image registration by utilizing image gray information can be overcome; the characteristics are matched with the characteristics of high speed and high matching efficiency; the matching elements are the geometric characteristics of the object, are insensitive to illumination change, and the matching result is less influenced by the illumination change and has higher accuracy.
Step A204, the image processing computer 2 calls an angular point matching module according to the matching feature pair set, performs angular point matching on a plurality of Harris angular points in the first frame image and a plurality of Harris angular points in the last frame image by adopting a normalized cross-correlation coefficient method, and finds out a one-to-one correspondence relationship between the plurality of Harris angular points in the first frame image and the plurality of Harris angular points in the last frame image;
in particular, the image processing computer 2 normalizes the cross-correlation coefficientsThe calculation formula of C is defined as:wherein I is the size of a window operated in the x-axis direction, -k is the lower limit of the window operated in the x-axis direction, k is the upper limit of the window operated in the x-axis direction, j is the size of the window operated in the y-axis direction, -l is the lower limit of the window operated in the y-axis direction, l is the upper limit of the window operated in the y-axis direction, and I (u + I, v + j) is the translation I of a Harris angular point I (u, v) in the first frame image in the x-axis direction and the translation j in the y-axis direction;is the average value of the gray levels in the corresponding window of the first frame imageI '(u' + I, v '+ j) is a Harris corner point I' (u ', v') in the last frame image, which is translated by I in the x-axis direction and by j in the y-axis direction;is the average value of the gray levels in the corresponding window of the last frame image andthe more the calculation result of the normalized cross-correlation coefficient C tends to 1, the stronger the correlation between the Harris corner point in the first frame image and the Harris corner point in the last frame image, and by comparing the calculation results of the normalized cross-correlation coefficient C, the one-to-one correspondence relationship between the plurality of Harris corner points in the first frame image and the plurality of Harris corner points in the last frame image is found.
Step a205, the image processing computer 2 calculates displacement values corresponding to each other between a plurality of Harris corners in the first frame image and a plurality of Harris corners in the last frame image, and calculates total displacement d of all Harris cornersTThen according to the formulaCalculating to obtain the position average value of all Harris angular pointsdA(ii) a Wherein, the corner (x) in the first frame image1,y1) And corner (x) in the last frame image1,y1) Corresponding corner point (x)2,y2) Corresponding displacement value d betweenrIs calculated by the formulaN is the total number of Harris angular points which have one-to-one correspondence relation with the last frame image in the first frame image, and the value of N is a positive integer;
step A206, the image processing computer 2 according to the formulaAnd calculating to obtain the vehicle running speed v, wherein D is the actual distance of the vehicle corresponding to the imaging area of the TOF camera 1, gamma is the number of frames of the last frame image moving relative to the first frame image, and η is the frame rate, namely the number of frames of images processed by the TOF camera 1 per second.
As shown in fig. 3, the method for recognizing the license plate of the vehicle based on TOF imaging of the invention comprises the following steps:
step B1, video acquisition and transmission: when a vehicle to be identified runs through an imaging area of the TOF camera 1, the TOF camera 1 shoots a plurality of frames of vehicle images and transmits shot multi-frame vehicle image signals to the image processing computer 2 in real time;
step B2, license plate recognition: and the image processing computer 2 calls a license plate recognition module to process the multi-frame vehicle images shot by the TOF cameras 1, and license plate characters are obtained through recognition.
In the step B2, the image processing computer 2 calls a license plate recognition module to process the multi-frame vehicle images shot by the plurality of TOF cameras 1, and the specific process of recognizing and obtaining license plate characters is as follows:
step B201, vehicle image preprocessing: the image processing computer 2 calls a vehicle image preprocessing module to preprocess the vehicle image and segment the license plate image from the original image;
in this embodiment, the image processing computer 2 in step B201 invokes a vehicle image preprocessing module to preprocess the vehicle image, and the specific process of segmenting the license plate image from the original image is as follows:
step B2011, gray level processing: the image processing computer 2 respectively performs gray level processing on a plurality of frames of vehicle images to generate a gray level histogram;
in the practical scene application of license plate recognition, due to the influences of various noise, illumination and other working environments and different factors of the TOF camera 1, the problems that the image quality of original image data is poor and the characteristics to be recognized are not obvious are avoided, and the operation of image preprocessing is carried out, so that the interference noise can be effectively eliminated, the image characteristics are clearer, and the stable and accurate work of a subsequent license plate recognition algorithm is ensured;
step B2012, edge operator detection: the image processing computer 2 adopts a Sobel operator to carry out edge operator detection processing on the image preprocessed in the step B2011;
the Sobel operator has the working characteristics that the gravity center is placed at a pixel point close to the center of a convolution template, the gray weighting algorithm of the horizontal and vertical adjacent points of the pixel point is utilized, the edge detection is carried out according to the phenomenon that an extreme value is reached at the edge point, and the Sobel operator has the advantage of having a certain inhibition effect on noise, so that when the Sobel operator is applied to the edge detection, the stable and accurate work of a subsequent license plate recognition algorithm can be ensured;
step B2013, edge contour rounding treatment: the image processing computer 2 calls an edge contour smoothing module to perform edge contour smoothing on the image processed in step B2012;
because the data source information of the license plate recognition image is complex, the minimum object in the image can be moved out to complete the initial positioning of the license plate through the smooth processing of the edge outline;
step B2014, license plate positioning and cutting: and the image processing computer 2 calls a license plate positioning module to perform license plate positioning on the image processed in the step B2013, determines a license plate area, and segments the license plate image from the original image.
In specific implementation, the method for segmenting the license plate image from the original image comprises the following steps: and finding out the maximum and minimum values of the line vectors and the maximum and minimum values of the column vectors in the boundary of the license plate area, thus determining four end points of the rectangle, and then cutting according to the coordinates of the four end points, thereby segmenting the license plate image from the original image.
Step B202, license plate recognition pretreatment: the image processing computer 2 calls a license plate processing module before license plate recognition to sequentially perform gray scale, binarization, mean value filtering and corrosion processing on the license plate image, and noise interference in the license plate image is filtered;
step B203, license plate character segmentation and recognition: the image processing computer 2 calls a license plate character segmentation and recognition module to segment and recognize license plate characters to obtain a license plate number.
In this embodiment, the image processing computer 2 in step B203 invokes a license plate character segmentation and recognition module to segment and recognize license plate characters, and the specific process of obtaining the license plate number is as follows:
step B2031, removing frames: the image processing computer 2 calls a frame removing processing module and removes the horizontal frame of the license plate image by adopting a horizontal projection method;
in specific implementation, firstly, performing horizontal projection on the license plate binary image obtained in the step 302, setting a threshold value according to the size characteristics of the frame and the wave crest and wave trough forms after the horizontal projection processing, performing removal processing on the frame in the horizontal direction, and selecting 1/10 of the width of the license plate as the threshold value according to the width proportional relation of the license plate frame in the license plate image data; then, with the center of the vertical coordinate axis of horizontal projection as a starting point, respectively finding out projection lines smaller than a threshold value from the edges in the upper direction and the lower direction, adjusting the sizes of the upper boundary and the lower boundary according to the projection lines, carrying out segmentation processing on the original image, and horizontally removing frames in a time limit manner;
step B2032, license plate character segmentation: the image processing computer 2 calls a license plate character segmentation module and segments license plate characters by combining a horizontal projection method and a vertical projection method;
in specific implementation, the height of the character is obtained through horizontal projection processing, and then the height nHeight of the character is obtained through calculation of the average pixel number contained in the front S column of the horizontal projection image data; obtaining the character spacing and the character width through vertical projection processing, and obtaining the maximum value of the spacing; scanning the top two rows of the vertical projection image, calculating the number of continuous black pixels and the number of continuous white pixels, calculating an average value, respectively recording the number of the continuous black pixels and the number of the continuous white pixels as a character interval nSpace and a character width nWidth, recording the maximum value of the character interval as a threshold nSpacemax, determining starting points of left and right scanning according to the obtained threshold, respectively scanning the vertical projection image of the license plate from the left and right of the two scanning starting points, judging the boundary of the character according to the size of the threshold and the sum of the black pixels on a certain column, determining five characters by right scanning, and determining two characters by left scanning;
step B2033, character normalization processing: the image processing computer 2 calls a character normalization processing module and calculates a character normalization value according to a formulaCarrying out normalization processing on the segmented license plate characters to obtain normalized license plate characters; wherein,in order to be able to normalize the character image before it,as the abscissa of the character image before normalization,has a value range ofHoldIn order to normalize the height of the character before it,is the ordinate of the character image before normalization,has a value range ofWoldThe character width before normalization;in order to be the normalized character image,as the abscissa of the normalized character image,has a value range ofHnewIn order to obtain the normalized height of the character,is the ordinate of the normalized character image,has a value range ofWnewThe normalized character width;
step B2034, license plate character recognition: the image processing computer 2 calls a license plate character recognition module and recognizes license plate characters by adopting a template matching method.
In this embodiment, when the image processing computer 2 in step B2034 calls the license plate character recognition module and recognizes the license plate characters by the template matching method, the specific process of establishing the template library is to divide each picture of each type of image into 8 parts on average, scan each picture region point by point, record and store the pixel information of the image in the form of a one-dimensional vector, and each character picture has a template formed by a corresponding 8-dimensional vector; equally dividing the license plate character image to be recognized into 8 parts, scanning each picture region point by point, recording and storing pixel information of the image in a one-dimensional vector form, determining 8-dimensional vector values of each character image, solving the 8-dimensional vector values of the characters and n-dimensional Euclidean space distances of the 8-dimensional vector values of all template character pictures, storing the 5 template character pictures with the minimum distance, and screening out possible solutions; then, setting a sum variable sum, comparing the character picture to be recognized with the 5 template character pictures stored before one by one, adding 1 to the same sum value, wherein the category of the template character picture with the largest sum value is the category of the character to be recognized, storing the category of the character to be recognized, and finally outputting the stored categories of the character pictures to be recognized of the whole license plate one by one in sequence to finish the character recognition of the whole license plate; wherein the value of n is a positive integer.
As will be appreciated by one skilled in the art, embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The present application is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the application. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
The foregoing descriptions of specific exemplary embodiments of the present invention have been presented for purposes of illustration and description. It is not intended to limit the invention to the precise form disclosed, and obviously many modifications and variations are possible in light of the above teaching. The exemplary embodiments were chosen and described in order to explain certain principles of the invention and its practical application to enable one skilled in the art to make and use various exemplary embodiments of the invention and various alternatives and modifications as are suited to the particular use contemplated. It is intended that the scope of the invention be defined by the claims and their equivalents.
Claims (10)
1. The utility model provides a vehicle speed of traveling and license plate identification system based on TOF formation of image which characterized in that: the system comprises a monitoring equipment mounting rack and a TOF camera (1) which are arranged on one side of a road, and an image processing computer (2) which is arranged in a monitoring center, is connected with the TOF camera (1) through a communication network and communicates with the TOF camera; the monitoring equipment mounting frame comprises a stand column (3-1) and a mounting rod (3-2) fixedly connected to the top of the stand column (3-1) and perpendicular to the stand column (3-1), and the TOF camera (1) is mounted at the top of the mounting rod (3-2).
2. The TOF imaging based vehicle speed and license plate recognition system of claim 1 wherein: the monitoring equipment mounting frame further comprises a rain baffle (3-3) arranged above the TOF camera (1), one end of the rain baffle (3-3) is fixedly connected to the top of the mounting rod (3-2) through a first supporting rod (3-4), and the other end of the rain baffle (3-3) is fixedly connected to the top of the mounting rod (3-2) through a second supporting rod (3-5).
3. A method for TOF imaging based vehicle speed identification using a system according to claim 1, comprising the steps of:
step A1, video acquisition and transmission: when a vehicle to be identified runs through an imaging area of the TOF camera (1), the TOF camera (1) shoots a plurality of frames of vehicle images and transmits shot multi-frame vehicle image signals to an image processing computer (2) in real time;
step A2, vehicle running speed identification: and the image processing computer (2) calls a vehicle running speed calculation module to process the multi-frame vehicle image shot by the TOF camera (1) and calculate to obtain the vehicle running speed.
4. A method according to claim 3, characterized by: in the step A2, the image processing computer (2) calls a vehicle running speed calculation module to process the multiframe vehicle images shot by the TOF camera (1), and the specific process of calculating the vehicle running speed is as follows:
step A201, the image processing computer (2) sets an imaging area of the TOF camera (1) as a speed measuring area;
a202, the image processing computer (2) detects a plurality of Harris angular points in a first frame image and a plurality of Harris angular points in a last frame image in a speed measurement area;
step A203, the image processing computer (2) calls a feature matching module to extract a feature set of a first frame image and a feature set of a last frame image, and the feature set of the first frame image and the feature set of the last frame image are matched and correspond to each other to generate a group of matching feature pair sets;
step A204, the image processing computer (2) calls an angular point matching module according to the matching feature pair set, performs angular point matching on a plurality of Harris angular points in the first frame image and a plurality of Harris angular points in the last frame image by adopting a normalized cross-correlation coefficient method, and finds out one-to-one correspondence between the plurality of Harris angular points in the first frame image and the plurality of Harris angular points in the last frame image;
step A205, the image processing computer (2) calculates displacement values corresponding to each other between a plurality of Harris corners in the first frame image and a plurality of Harris corners in the last frame image, and calculates total displacement d of all Harris cornersTThen according to the formulaCalculating to obtain the position average value d of all Harris angular pointsA(ii) a Wherein, the corner (x) in the first frame image1,y1) And corner (x) in the last frame image1,y1) Corresponding corner point (x)2,y2) Corresponding displacement value d betweenrIs calculated by the formulaN is the total number of Harris angular points which have one-to-one correspondence relation with the last frame image in the first frame image, and the value of N is a positive integer;
step A206, the image processing computer (2) according to the formulaAnd calculating to obtain the vehicle running speed v, wherein D is the actual vehicle running distance corresponding to the imaging area of the TOF camera (1), gamma is the number of frames of the movement of the last frame image relative to the first frame image, and η is the frame rate.
5. The method of claim 4, wherein: in step a202, when the image processing computer (2) detects multiple Harris corners in the first frame of image and multiple Harris corners in the last frame of image in the velocity measurement area, the process of detecting the multiple Harris corners in the image I (x, y) is as follows:
step A2021, the image processing computer (2) according to the formulaCalculating the gradient I of the image I (x, y) in the direction of the x-axisxAccording to the formulaCalculating the gradient I of the image I (x, y) in the y-axis directiony；
Step 2022, the image processing computer (2) calculates the correlation matrix on each pixelWherein ω (x, y) is a weighting function;
step a2023, the image processing computer (2) sets (ab-c) to (R) according to the formula2)-λ(a+b)2Calculating a corner response value R of each pixel point; wherein lambda is an empirical constant and has a value range of 0.04-0.06;
step A2024, the image processing computer (2) searches a maximum value point of the corner response value in an M × M square range at the middle position on the image I (x, y), defines the found maximum value point of the corner response value as a threshold, and determines a pixel point as a Harris corner when the corner response value R of the pixel point is greater than the threshold.
6. A method for TOF imaging based license plate recognition of vehicles using the system according to claim 1, comprising the steps of:
step B1, video acquisition and transmission: when a vehicle to be identified runs through an imaging area of the TOF camera (1), the TOF camera (1) shoots a plurality of frames of vehicle images and transmits shot multi-frame vehicle image signals to an image processing computer (2) in real time;
step B2, license plate recognition: and the image processing computer (2) calls a license plate recognition module to process the multi-frame vehicle images shot by the TOF cameras (1) and recognize the images to obtain license plate characters.
7. The method of claim 6, wherein: in the step B2, the image processing computer (2) calls a license plate recognition module to process the multiframe vehicle images shot by the TOF cameras (1), and the specific process of recognizing and obtaining license plate characters is as follows:
step B201, vehicle image preprocessing: the image processing computer (2) calls a vehicle image preprocessing module to preprocess the vehicle image and segment the license plate image from the original image;
step B202, license plate recognition pretreatment: the image processing computer (2) calls a license plate processing module before license plate recognition to sequentially perform gray scale, binarization, mean value filtering and corrosion processing on the license plate image, and noise interference in the license plate image is filtered;
step B203, license plate character segmentation and recognition: and the image processing computer (2) calls a license plate character segmentation and recognition module to segment and recognize license plate characters to obtain a license plate number.
8. The method of claim 7, wherein: in the step B201, the image processing computer (2) calls a vehicle image preprocessing module to preprocess the vehicle image, and the specific process of segmenting the license plate image from the original image is as follows:
step B2011, gray level processing: the image processing computer (2) respectively carries out gray level processing on a plurality of frames of vehicle images to generate a gray level histogram;
step B2012, edge operator detection: the image processing computer (2) adopts a Sobel operator to carry out edge operator detection processing on the image preprocessed in the step B2011;
step B2013, edge contour rounding treatment: the image processing computer (2) calls an edge contour smoothing module to perform edge contour smoothing on the image processed in the step B2012;
step B2014, license plate positioning and cutting: and the image processing computer (2) calls a license plate positioning module to perform license plate positioning on the image processed in the step B2013, determines a license plate area, and segments the license plate image from the original image.
9. The method of claim 7, wherein: in the step B203, the image processing computer (2) calls a license plate character segmentation and recognition module to segment and recognize license plate characters, and the specific process of obtaining the license plate number is as follows:
step B2031, removing frames: the image processing computer (2) calls a frame removing processing module and removes the horizontal frame of the license plate image by adopting a horizontal projection method;
step B2032, license plate character segmentation: the image processing computer (2) calls a license plate character segmentation module and segments license plate characters by combining a horizontal projection method and a vertical projection method;
step B2033, character normalization processing: the image processing computer (2) calls a character normalization processing module and calculates the normalization value according to a formulaCarrying out normalization processing on the segmented license plate characters to obtain normalized license plate characters; wherein,in order to be able to normalize the character image before it,as the abscissa of the character image before normalization,has a value range ofHoldIn order to normalize the height of the character before it,is the ordinate of the character image before normalization,has a value range ofWoldThe character width before normalization;in order to be the normalized character image,as the abscissa of the normalized character image,has a value range ofHnewIn order to obtain the normalized height of the character,is the ordinate of the normalized character image,has a value range ofWnewThe normalized character width;
step B2034, license plate character recognition: and the image processing computer (2) calls a license plate character recognition module and recognizes the license plate characters by adopting a template matching method.
10. The method of claim 9, wherein: b2034, when the image processing computer (2) calls the license plate character recognition module and recognizes the license plate characters by adopting a template matching method, the specific process of establishing the template library is to averagely divide each picture of each type of images into 8 parts, scan each picture region point by point, record and store the pixel information of the images in a one-dimensional vector form, and each character picture is provided with a template formed by corresponding 8-dimensional vectors; equally dividing the license plate character image to be recognized into 8 parts, scanning each picture region point by point, recording and storing pixel information of the image in a one-dimensional vector form, determining 8-dimensional vector values of each character image, solving the 8-dimensional vector values of the characters and n-dimensional Euclidean space distances of the 8-dimensional vector values of all template character pictures, storing the 5 template character pictures with the minimum distance, and screening out possible solutions; then, setting a sum variable sum, comparing the character picture to be recognized with the 5 template character pictures stored before one by one, adding 1 to the same sum value, wherein the category of the template character picture with the largest sum value is the category of the character to be recognized, storing the category of the character to be recognized, and finally outputting the stored categories of the character pictures to be recognized of the whole license plate one by one in sequence to finish the character recognition of the whole license plate; wherein the value of n is a positive integer.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811401087.8A CN109543613A (en) | 2018-11-22 | 2018-11-22 | Vehicle Speed and Vehicle License Plate Recognition System and method based on TOF imaging |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811401087.8A CN109543613A (en) | 2018-11-22 | 2018-11-22 | Vehicle Speed and Vehicle License Plate Recognition System and method based on TOF imaging |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109543613A true CN109543613A (en) | 2019-03-29 |
Family
ID=65850375
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811401087.8A Pending CN109543613A (en) | 2018-11-22 | 2018-11-22 | Vehicle Speed and Vehicle License Plate Recognition System and method based on TOF imaging |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109543613A (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110942663A (en) * | 2019-12-02 | 2020-03-31 | 北京深测科技有限公司 | Monitoring distribution guiding method and system for parking lot |
| CN110992729A (en) * | 2019-12-25 | 2020-04-10 | 深圳人人停技术有限公司 | Reserved parking management method, device, equipment and medium |
| CN111369806A (en) * | 2020-03-12 | 2020-07-03 | 山东泰安煤矿机械有限公司 | Method and device for photographing, measuring speed and identifying license plate of freight train |
| CN112750313A (en) * | 2020-12-31 | 2021-05-04 | 上海易维视科技有限公司 | FPGA-based video acquisition and parking lot license plate recognition system and method |
| CN117152732A (en) * | 2023-10-18 | 2023-12-01 | 北京精英智通科技股份有限公司 | Multi-feature-assisted license plate recognition method and system |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20100046802A1 (en) * | 2008-08-19 | 2010-02-25 | Tatsumi Watanabe | Distance estimation apparatus, distance estimation method, storage medium storing program, integrated circuit, and camera |
| CN103686083A (en) * | 2013-12-09 | 2014-03-26 | 北京理工大学 | Real-time speed measurement method based on vehicle-mounted sensor video streaming matching |
| CN104156704A (en) * | 2014-08-04 | 2014-11-19 | 胡艳艳 | Novel license plate identification method and system |
| US20160018904A1 (en) * | 2010-05-20 | 2016-01-21 | Edge3 Technologies Llc | Gesture Recognition in Vehicles |
| CN205247621U (en) * | 2015-12-24 | 2016-05-18 | 北京万集科技股份有限公司 | Thing detection device is dropped to vehicle based on TOF camera |
| CN105628951A (en) * | 2015-12-31 | 2016-06-01 | 北京小孔科技有限公司 | Method and device for measuring object speed |
-
2018
- 2018-11-22 CN CN201811401087.8A patent/CN109543613A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20100046802A1 (en) * | 2008-08-19 | 2010-02-25 | Tatsumi Watanabe | Distance estimation apparatus, distance estimation method, storage medium storing program, integrated circuit, and camera |
| US20160018904A1 (en) * | 2010-05-20 | 2016-01-21 | Edge3 Technologies Llc | Gesture Recognition in Vehicles |
| CN103686083A (en) * | 2013-12-09 | 2014-03-26 | 北京理工大学 | Real-time speed measurement method based on vehicle-mounted sensor video streaming matching |
| CN104156704A (en) * | 2014-08-04 | 2014-11-19 | 胡艳艳 | Novel license plate identification method and system |
| CN205247621U (en) * | 2015-12-24 | 2016-05-18 | 北京万集科技股份有限公司 | Thing detection device is dropped to vehicle based on TOF camera |
| CN105628951A (en) * | 2015-12-31 | 2016-06-01 | 北京小孔科技有限公司 | Method and device for measuring object speed |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110942663A (en) * | 2019-12-02 | 2020-03-31 | 北京深测科技有限公司 | Monitoring distribution guiding method and system for parking lot |
| CN110992729A (en) * | 2019-12-25 | 2020-04-10 | 深圳人人停技术有限公司 | Reserved parking management method, device, equipment and medium |
| CN111369806A (en) * | 2020-03-12 | 2020-07-03 | 山东泰安煤矿机械有限公司 | Method and device for photographing, measuring speed and identifying license plate of freight train |
| CN112750313A (en) * | 2020-12-31 | 2021-05-04 | 上海易维视科技有限公司 | FPGA-based video acquisition and parking lot license plate recognition system and method |
| CN117152732A (en) * | 2023-10-18 | 2023-12-01 | 北京精英智通科技股份有限公司 | Multi-feature-assisted license plate recognition method and system |
| CN117152732B (en) * | 2023-10-18 | 2024-02-27 | 北京精英智通科技股份有限公司 | Multi-feature-assisted license plate recognition method and system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109543613A (en) | Vehicle Speed and Vehicle License Plate Recognition System and method based on TOF imaging | |
| CN108596129B (en) | Vehicle line-crossing detection method based on intelligent video analysis technology | |
| CN109101924B (en) | Machine learning-based road traffic sign identification method | |
| CN103324930B (en) | A kind of registration number character dividing method based on grey level histogram binaryzation | |
| CN107315095B (en) | More vehicle automatic speed-measuring methods with illumination adaptability based on video processing | |
| CN103065138B (en) | Recognition method of license plate number of motor vehicle | |
| CN110379168B (en) | Traffic vehicle information acquisition method based on Mask R-CNN | |
| CN110647850A (en) | Automatic lane deviation measuring method based on inverse perspective principle | |
| US9189691B2 (en) | Three-dimensional object detection device and three-dimensional object detection method | |
| Li et al. | Nighttime lane markings recognition based on Canny detection and Hough transform | |
| CN107945523B (en) | Road vehicle detection method, traffic parameter detection method and device | |
| CN103077384A (en) | Method and system for positioning and recognizing vehicle logo | |
| CN110414355A (en) | The right bit sky parking stall of view-based access control model and parking stall line detecting method during parking | |
| CN108205667A (en) | Method for detecting lane lines and device, lane detection terminal, storage medium | |
| CN1448886A (en) | Apparatus and method for measuring vehicle queue length | |
| CN107895151A (en) | Method for detecting lane lines based on machine vision under a kind of high light conditions | |
| CN107845264A (en) | A kind of volume of traffic acquisition system and method based on video monitoring | |
| US20200125869A1 (en) | Vehicle detecting method, nighttime vehicle detecting method based on dynamic light intensity and system thereof | |
| CN104378539B (en) | The video structural extraction of semantics video camera and its method of scene adaptive | |
| CN111476804A (en) | Method, device and equipment for efficiently segmenting carrier roller image and storage medium | |
| CN104063882A (en) | Vehicle video speed measuring method based on binocular camera | |
| CN105303157A (en) | Algorithm to extend detecting range for AVM stop line detection | |
| CN111368797A (en) | Target real-time ranging method based on road end monocular camera | |
| CN108520528B (en) | Mobile vehicle tracking method based on improved difference threshold and displacement matching model | |
| Jiang et al. | Lane line detection optimization algorithm based on improved Hough transform and R-least squares with dual removal |
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 |