CN113362612A - Vehicle identification method and system - Google Patents
Vehicle identification method and system Download PDFInfo
- Publication number
- CN113362612A CN113362612A CN202110613489.XA CN202110613489A CN113362612A CN 113362612 A CN113362612 A CN 113362612A CN 202110613489 A CN202110613489 A CN 202110613489A CN 113362612 A CN113362612 A CN 113362612A
- Authority
- CN
- China
- Prior art keywords
- vehicle
- value
- historical
- color
- score
- 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 40
- 230000001815 facial effect Effects 0.000 claims description 34
- 239000001055 blue pigment Substances 0.000 claims description 31
- 239000001056 green pigment Substances 0.000 claims description 31
- 239000001054 red pigment Substances 0.000 claims description 17
- 238000004891 communication Methods 0.000 claims description 6
- 230000003247 decreasing effect Effects 0.000 claims description 6
- SBNFWQZLDJGRLK-UHFFFAOYSA-N phenothrin Chemical compound CC1(C)C(C=C(C)C)C1C(=O)OCC1=CC=CC(OC=2C=CC=CC=2)=C1 SBNFWQZLDJGRLK-UHFFFAOYSA-N 0.000 claims description 5
- 239000000126 substance Substances 0.000 claims description 3
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000013077 scoring method Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Images
Classifications
-
- 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
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Image Analysis (AREA)
Abstract
The invention discloses a vehicle identification method and a system, wherein the method comprises the following steps: step 1, obtaining a vehicle head image; step 2, acquiring four kinds of vehicle characteristic data from the vehicle head image; step 3, acquiring all historical vehicle characteristic data from a historical vehicle characteristic database; step 4, correspondingly comparing the acquired vehicle characteristic data with all acquired historical vehicle characteristic data to obtain each characteristic score; and 5, taking the vehicle determined by the result with the highest score in the feature score sums as the finally identified vehicle identification result. Compared with the traditional vehicle identification method, the method disclosed by the invention does not only rely on the identification of the license plate, but also identifies the color, the sign, the driver and other characteristics of the vehicle while identifying the license plate, so that the vehicle with the dirty license plate can be effectively identified, and the accuracy of vehicle identification is improved.
Description
Technical Field
The invention relates to the field of vehicle identity recognition, in particular to a vehicle recognition method and system.
Background
The existing vehicle identification method mainly identifies the vehicle identity by identifying the license plate number and confirming the vehicle identity through the identified license plate number, thereby realizing the identification authentication of the vehicle.
However, in the process of identifying the license plate number in an image identification mode, if dirt exists on the license plate number, the accuracy of license plate number identification is affected, and the identity of the vehicle is confirmed by the obtained license plate number, so that more misjudgments are often generated.
Disclosure of Invention
Based on the problems existing in the prior art, the invention aims to provide a vehicle number plate identification method, which can solve the problems that the existing vehicle identification is realized by identifying the number plate number in an image identification mode, but the vehicle number plate is dirty, so that the identification result is inaccurate, and more vehicle identities are prone to be misjudged.
The purpose of the invention is realized by the following technical scheme:
an embodiment of the present invention provides a vehicle identification method, including:
step 1, obtaining a vehicle head image of an identified vehicle, wherein the horizontal identifiable pixels of the vehicle head image are not less than 800 pixels, and the shooting angle of the vehicle head image is not more than 30 degrees when the front part of the identified vehicle horizontally deviates from the central axis of the vehicle;
(21) vehicle color characteristics: the proportion of color pixels in a preset color group in the vehicle head image pixels is represented, and the representation is represented by the following format:
RGbn, which is the proportion of pixel value groups in the RGB value range in the whole vehicle head image pixels; in the RGBN value, the R value is a haematochrome value range, and the format is an initial value and a final value; the G value range is a green pigment value range, and the format is an initial value and a final value; the B value range is a blue pigment value range, and the format is an initial value and a final value; n represents the number of groups of pixel value groups in the RGB pixel range; the difference value between the initial value and the final value of the value ranges of the red, green and blue pigments is not more than 20, and 1, 3, 5, 10 and 20 can be selected;
(22) vehicle brand logo features: obtaining the color characteristics of the position area of the vehicle brand mark in the vehicle head image, comparing the color characteristics with the color characteristics of the position area of the brand mark of the collected sample image of the existing typical vehicle type, and selecting the vehicle brand mark corresponding to the maximum value in all comparison results as the vehicle brand mark characteristics;
the color characteristics of the vehicle brand mark position area are represented by the following format:
RGbn, which is the proportion of pixel value groups in the RGB value range in the pixels of the whole vehicle brand mark position area image; in the RGBN value, the R value is a haematochrome value range, and the format is an initial value and a final value; the G value range is a green pigment value range, and the format is an initial value and a final value; the B value range is a blue pigment value range, and the format is an initial value and a final value; n represents the number of groups of pixel value groups in the RGB pixel range; the difference value between the initial value and the final value of the value ranges of the red, green and blue pigments is not more than 20, and 1, 3, 5, 10 and 20 can be selected;
(23) vehicle driver facial feature code: if the driver position in the vehicle head image is judged to be a face, recognizing a face feature code of the driver position as a face feature code of a vehicle driver;
(24) vehicle number plate recognizing section: identifying vehicle number plate characters from the vehicle number plate part in the vehicle head image;
step 4, scoring historical characteristic data: comparing the vehicle characteristic data obtained in the step 2 with the historical vehicle characteristic data obtained in the step 3 to obtain a score of each characteristic comparison, wherein the scoring mode of each score is as follows:
(41) historical vehicle color feature score: calculating vehicle color feature scores according to vehicle color feature matching degrees, wherein the vehicle color feature matching degrees adopt n groups of pixel value group ratios with the largest pixel value group ratio for matching, when the red pigment value, the green pigment value and the blue pigment value of the matched color features are overlapped and the ratio error is within 5%, the matching is successful, the pixel value group ratios which are successfully matched are arranged from large to small, the matching item scores are decreased, the weights of the matching item scores are set from large to small, and the matching item scores of all the pixel value groups are added to obtain historical vehicle color feature scores;
(42) historical vehicle brand signature feature score: matching color features according to the vehicle brand mark features and the historical vehicle brand mark features, wherein the matching color feature mode is the same as the matching mode in the historical vehicle color feature score;
(43) the historical vehicle driver facial feature codes are scored, the obtained vehicle driver facial feature codes are compared with the historical vehicle driver facial feature codes, and if all vehicles which can be matched with the driver facial feature codes are obtained, the driver feature codes of the vehicles are full marks;
(44) the historical vehicle license plate scores, the obtained vehicle license plate identification part is matched with the historical vehicle license plate, a corresponding score is obtained every time one character or letter is successfully matched according to the same direction sequence, and the sum of the scores after all the characters or letters are matched is the historical vehicle license plate score;
and 5, selecting the result with the highest score as a vehicle identification result, and judging the score according to the following modes:
and multiplying each feature comparison score by the corresponding weight to obtain the feature score, adding all the feature scores to obtain a total score, and selecting the result with the highest total score as the vehicle identification result.
The embodiment of the invention also provides a vehicle identification system, which is used for realizing the method provided by the invention and comprises the following steps:
the system comprises a shooting device, a vehicle identification server, a vehicle characteristic data historical database and a vehicle identification result output device; wherein the content of the first and second substances,
the shooting device is in communication connection with the vehicle identification server, can acquire a vehicle head image of the identified vehicle and sends the vehicle head image to the vehicle identification server;
the vehicle identification server is respectively in communication connection with the vehicle characteristic data historical database and the vehicle identification result output device, can identify vehicle characteristic data from the vehicle head image obtained in the step 1 through image identification, can obtain all historical vehicle characteristic data from the vehicle characteristic data historical database, and obtains a score of each feature comparison by comparing the obtained vehicle characteristic data with the historical vehicle characteristic data, selects a result with the highest score as a vehicle identification result, and sends the vehicle identification result to the vehicle identification result output device;
and the vehicle identification result output device outputs the vehicle identification result obtained by the vehicle identification server.
According to the technical scheme provided by the invention, the vehicle identification method provided by the embodiment of the invention has the beneficial effects that:
at least two kinds of vehicle characteristic data are obtained from the adopted images, and the vehicle identity is not confirmed by only identifying the vehicle number plate any more.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings needed to be used in the description of the embodiments are briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art to obtain other drawings based on the drawings without creative efforts.
FIG. 1 is a flow chart of a vehicle identification method provided by an embodiment of the invention;
FIG. 2 is a flowchart illustrating a detailed process of a vehicle identification method according to an embodiment of the present invention;
fig. 3 is a schematic configuration diagram of a vehicle identification system according to an embodiment of the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention are clearly and completely described below with reference to the specific contents of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments of the present invention without making any creative effort, shall fall within the protection scope of the present invention. Details which are not described in detail in the embodiments of the invention belong to the prior art which is known to the person skilled in the art.
As shown in fig. 1 and 2, an embodiment of the present invention provides a vehicle identification method, including:
step 1, obtaining a vehicle head image of an identified vehicle, wherein the horizontal identifiable pixels of the vehicle head image are not less than 800 pixels, and the shooting angle of the vehicle head image is not more than 30 degrees when the front part of the identified vehicle horizontally deviates from the central axis of the vehicle;
(21) vehicle color characteristics: the vehicle color feature is expressed by the proportion of color pixels in a predetermined color group in the vehicle head image pixels, and is expressed by the following format:
RGbn, which is the proportion of pixel value groups in the RGB value range in the whole vehicle head image pixels; in the RGBN value, the R value is a haematochrome value range, and the format is (initial value and termination value); the G value range is a green pigment value range, and the format is (initial value and final value); the B value range is a blue pigment value range, and the format is (initial value and termination value); n represents the number of groups of pixel value groups in the RGB pixel range; the difference value between the initial value and the final value of the value ranges of the red, green and blue pigments is not more than 20, and 1, 3, 5, 10 and 20 can be selected; the difference between the starting value and the ending value of red, green and blue can be set to the same value or different values;
(22) vehicle brand logo features: obtaining the color characteristics of the position area of the vehicle brand mark in the vehicle head image, comparing the color characteristics with the color characteristics of the position area of the brand mark of the collected sample image of the existing typical vehicle type, and selecting the vehicle brand mark corresponding to the maximum value in all comparison results as the vehicle brand mark characteristics;
the color characteristics of the vehicle brand mark position area are represented by the following format:
RGbn, which is the proportion of pixel value groups in the RGB value range in the pixels of the whole vehicle brand mark position area image; in the RGBN value, the R value is a haematochrome value range, and the format is (initial value and termination value); the G value range is a green pigment value range, and the format is (initial value and final value); the B value range is a blue pigment value range, and the format is (initial value and termination value); n represents the number of groups of pixel value groups in the RGB pixel range; the difference value between the initial value and the final value of the value ranges of the red, green and blue pigments is not more than 20, and 1, 3, 5, 10 and 20 can be selected; the difference between the starting value and the ending value of red, green and blue can be set to the same value or different values;
(23) vehicle driver facial feature code: if the driver position in the vehicle head image is judged to be a face, recognizing a face feature code of the driver position as a face feature code of a vehicle driver;
(24) vehicle number plate recognizing section: identifying vehicle number plate characters from the vehicle number plate part in the vehicle head image;
step 4, scoring historical characteristic data: comparing the vehicle characteristic data obtained in the step 2 with the historical vehicle characteristic data obtained in the step 3 to obtain a score of each characteristic comparison, wherein the scoring mode of each score is as follows:
(41) historical vehicle color feature score: calculating vehicle color feature scores according to vehicle color feature matching degrees, wherein the vehicle color feature matching degrees adopt n groups of pixel value group ratios with the largest pixel value group ratio for matching, when the red pigment value, the green pigment value and the blue pigment value of the matched color features are overlapped and the ratio error is within 5%, the matching is successful, the pixel value group ratios which are successfully matched are arranged from large to small, the matching item scores are decreased, the weights of the matching item scores are set from large to small, and the matching item scores of all the pixel value groups are added to obtain historical vehicle color feature scores;
(42) historical vehicle brand signature feature score: matching color features according to the vehicle brand mark features and the historical vehicle brand mark features, wherein the matching color feature mode is the same as the matching mode in the historical vehicle color feature score;
(43) the historical vehicle driver facial feature codes are scored, the obtained vehicle driver facial feature codes are compared with the historical vehicle driver facial feature codes, and if all vehicles which can be matched with the driver facial feature codes are obtained, the driver feature codes of the vehicles are full marks;
(44) the historical vehicle license plate scores, the obtained vehicle license plate identification part is matched with the historical vehicle license plate, a corresponding score is obtained every time one character or letter is successfully matched according to the same direction sequence, and the sum of the scores after all the characters or letters are matched is the historical vehicle license plate score;
and 5, selecting the result with the highest score as a vehicle identification result, and judging the score according to the following modes:
and multiplying each feature comparison score by the corresponding weight to obtain the feature score, adding all the feature scores to obtain a total score, and selecting the result with the highest total score as the vehicle identification result.
In step 5 of the above method, the order of the weights corresponding to the feature comparison scores is as follows:
the first weight ratio is: scoring historical vehicle number plates;
the second weight ratio is: historical vehicle color feature scores;
the third weight ratio: historical brand logo feature scores;
the fourth weight ratio: historical vehicle driver facial feature code scores.
The first weight proportion is larger than the second weight proportion, the second weight proportion is larger than the third weight proportion, and the third weight proportion is larger than the fourth weight proportion. Preferably, the weight ratios are respectively distributed according to the following proportion, as long as the sum of the 4 weight ratios is 100%, the first weight ratio is 30-50%, the second weight ratio is 20-30%, the third weight ratio is 15-20%, and the fourth weight ratio is 5-15%. And the weight proportion of other proportions can be adopted according to the requirement, so long as the identity of the vehicle can be accurately identified.
The method further comprises the following steps after the step 5: and 6, storing the current vehicle identification result and the vehicle characteristic data into a vehicle characteristic data historical database.
In the step 2 of the method, the color characteristics of the brand mark position area of the collected sample map of the existing typical vehicle model are determined in the following way:
collecting a sample map of an existing vehicle brand and a typical vehicle type, marking a brand mark position area in the sample map, and obtaining the color characteristics of the marked brand mark position area in the sample map through image recognition, wherein the color characteristics are represented by the following format:
RGbn, which is the proportion of pixel value groups in the RGB value range in the whole brand mark position area image pixels; in the RGBN value, the R value is a haematochrome value range, and the format is an initial value and a final value; the G value range is a green pigment value range, and the format is (initial value, end value); the B value range is a blue pigment value range, and the format is an initial value and a final value); n represents the number of groups of pixel value groups in the RGB pixel range; the difference value between the initial value and the final value of the value ranges of the red, green and blue pigments is not more than 20, and 1, 3, 5, 10 and 20 can be selected; the difference between the starting value and the ending value of red, green, blue may be set to the same value or different values.
Preferably, the head image of the vehicle acquired in step 1 is an image with a definition recognizable by a computer, and may be captured by a camera or a digital camera, or an existing image may be used to acquire the head image of the recognized vehicle, where the horizontal recognizable pixel of the head image of the vehicle is required to be not less than 800 pixels, the head of the vehicle can be completely displayed in the image, the image capturing angle is located at the front of the vehicle, the horizontal deviation angle from the central axis of the vehicle is not more than 30 degrees (0 degree, 15 degrees off the left, 20 degrees off the left, 25 degrees off the left, 30 degrees off the right, 15 degrees off the right, 25 degrees off the right, 30 degrees off the right can be selected), and the longitudinal deviation angle from the central axis of the vehicle is not more than 30 degrees (0 degree, 15 degrees off the top, 20 degrees off the top, 25 degrees off the top, 30 degrees off the top, 15 degrees off the bottom, 20 degrees off the bottom, 25 degrees off the bottom, 30 degrees off the bottom can be selected).
As shown in fig. 3, an embodiment of the present invention further provides a vehicle identification system, which is configured to implement the foregoing method, and includes:
a photographing device 101, a vehicle recognition server 102, a vehicle feature data history database 104, and a vehicle recognition result output device 103; wherein the content of the first and second substances,
the shooting device is in communication connection with the vehicle identification server, can acquire a vehicle head image of the identified vehicle and sends the vehicle head image to the vehicle identification server;
the vehicle identification server is respectively in communication connection with the vehicle characteristic data historical database and the vehicle identification result output device, can identify vehicle characteristic data from the vehicle head image obtained in the step 1 through image identification, can obtain all historical vehicle characteristic data from the vehicle characteristic data historical database, and obtains a score of each feature comparison by comparing the obtained vehicle characteristic data with the historical vehicle characteristic data, selects a result with the highest score as a vehicle identification result, and sends the vehicle identification result to the vehicle identification result output device;
and the vehicle identification result output device outputs the vehicle identification result obtained by the vehicle identification server.
In the above system, the vehicle recognition result output device includes: at least one of a graphic display device and a sound playing device.
In the system, the shooting device adopts at least one of a camera and a terminal with the camera.
The above system further comprises: the vehicle identification server stores the identification result to the vehicle characteristic data history database.
In the above system, the vehicle feature data recognized by the vehicle recognition server includes:
(21) vehicle color features, represented in the following format:
RGbn, which is the proportion of pixel value groups in the RGB value range in the whole vehicle head image pixels; in the RGBN value, the R value is a haematochrome value range, and the format is (initial value and termination value); the G value range is a green pigment value range, and the format is (initial value and final value); the B value range is a blue pigment value range, and the format is (initial value and termination value); n represents the number of groups of pixel value groups in the RGB pixel range; the difference value between the initial value and the final value of the value ranges of the red, green and blue pigments is not more than 20, and 1, 3, 5, 10 and 20 can be selected; the difference between the starting value and the ending value of red, green and blue can be set to the same value or different values;
(22) vehicle brand logo features: obtaining the color characteristics of the position area of the vehicle brand mark in the vehicle head image, comparing the color characteristics with the color characteristics of the position area of the brand mark of the collected sample image of the existing typical vehicle type, and selecting the vehicle brand mark corresponding to the maximum value in all comparison results as the vehicle brand mark characteristics;
the color characteristics of the vehicle brand mark position area are represented by the following format:
RGbn, which is the proportion of pixel value groups in the RGB value range in the pixels of the whole vehicle brand mark position area image; in the RGBN value, the R value is a haematochrome value range, and the format is (initial value and termination value); the G value range is a green pigment value range, and the format is (initial value and final value); the B value range is a blue pigment value range, and the format is (initial value and termination value); n represents the number of groups of pixel value groups in the RGB pixel range; the difference value between the initial value and the final value of the value ranges of the red, green and blue pigments is not more than 20, and 1, 3, 5, 10 and 20 can be selected; the difference between the starting value and the ending value of red, green and blue can be set to the same value or different values;
(23) vehicle driver facial feature code: if the driver position in the vehicle head image is judged to be a face, recognizing a face feature code of the driver position as a face feature code of a vehicle driver;
(24) vehicle number plate recognizing section: and identifying vehicle number plate characters from the vehicle number plate part in the vehicle head image.
In the above system, the scoring method for the vehicle identification server to obtain each feature comparison score by comparing the obtained vehicle feature data with the historical vehicle feature data includes:
(41) historical vehicle color feature score: calculating vehicle color feature scores according to vehicle color feature matching degrees, wherein the vehicle color feature matching degrees adopt n groups of pixel value group ratios with the largest color pixel number ratio for matching, when the red value, the green value and the blue value of the matched color features are overlapped and the ratio error is within 5%, the matching is successful, the pixel value group ratios which are successfully matched are arranged from large to small, the matching scores are decreased, the weights are set according to the sequence from large to small for each matching score, and the matching scores of all color value groups are added to obtain historical vehicle color feature scores;
(42) historical vehicle brand signature feature score: matching color features according to the vehicle brand mark features and the historical vehicle brand mark features, wherein the matching color feature mode is the same as the matching mode in the historical vehicle color feature score;
(43) the historical vehicle driver facial feature codes are scored, the obtained vehicle driver facial feature codes are compared with the historical vehicle driver facial feature codes, and if all vehicles which can be matched with the driver facial feature codes are obtained, the driver feature codes of the vehicles are full marks;
(44) and scoring the historical vehicle license plate, matching the obtained vehicle license plate recognition part with the historical vehicle license plate, obtaining a corresponding score for each character or letter matched successfully according to the same direction sequence, wherein the sum of the scores after all the characters or letters are matched is the score of the historical vehicle license plate.
Preferably, the face recognition and the license plate recognition in the method can adopt a mature algorithm provided by the prior art, such as an iridescent ArcSoft face recognition SDK packet (see the website: https:// ai. ArcSoft. com. cn /), a salary technology vehicle license plate recognition SDK (see the website: https:// www.xinhuokj.com/ocr/car), and the like.
Compared with the traditional vehicle identification method, the method provided by the invention does not only rely on the identification of the license plate, but also identifies the license plate, and simultaneously comprises a plurality of characteristics of identifying the color, the mark, the driver and the like of the vehicle, so that the vehicle license plate identification can be effectively carried out on the vehicle with the dirty license plate, and the accuracy of the vehicle identification is improved.
The embodiments of the present invention are described in further detail below.
The first embodiment is as follows:
the following steps are adopted to identify the vehicle, and the identification result is stored in a database. The flow of the vehicle identification method is specifically shown in fig. 2, and the vehicle identification method comprises the following steps:
starting, the car number identification work is started;
step 1, obtaining a vehicle head image. The method comprises the steps of obtaining a head image of an identified vehicle through a camera or a digital camera or an existing image, wherein the horizontal identifiable pixel of the head image of the vehicle is required to be not less than 800 pixels, the head of the vehicle can be completely displayed in the image, the image shooting angle is located at the front of the vehicle, is horizontally deviated from the central axis of the vehicle by not more than 30 degrees (0 degree, 15 degrees, 20 degrees, 25 degrees, 30 degrees, 15 degrees, 20 degrees, 25 degrees and 30 degrees), and the image shooting angle is located at the front of the vehicle, is horizontally deviated from the central axis of the vehicle by not more than 30 degrees (0 degree, 15 degrees, 20 degrees, 25 degrees, 30 degrees, 15 degrees, 20 degrees, 25 degrees and 30 degrees);
(21) identifying the color features of the vehicle: the vehicle color feature is represented by the proportion of color pixels in a predetermined color group in the vehicle head image pixels, and adopts the following format:
RGbn, which is the proportion of pixel value groups in the RGB value range in the whole vehicle head image pixels; in the RGBN value, the R value is a haematochrome value range, and the format is (initial value and termination value); the G value range is a green pigment value range, and the format is (initial value and final value); the B value range is a blue pigment value range, and the format is (initial value and termination value); n represents the number of groups of RGB pixel range value groups; the difference value between the initial value and the final value of the value ranges of the red, green and blue pigments is not more than 20, and 1, 3, 5, 10 and 20 can be selected; the difference between the starting value and the ending value of red, green and blue can be set to the same value or different values;
(22) recognizing a vehicle brand mark: the method comprises the steps of collecting sample pictures of the existing vehicle brands and typical vehicle types, marking the position areas of the brand marks, analyzing the color characteristics of the areas, and enabling the formats of the color characteristics to be as follows:
RGbn, which is the proportion of pixel value groups in the RGB value range in the whole brand mark position area image pixels; in the RGBN value, the R value is a haematochrome value range, and the format is (initial value and termination value); the G value range is a green pigment value range, and the format is (initial value and final value); the B value range is a blue pigment value range, and the format is (initial value and termination value); n represents the number of groups of RGB pixel range value groups; the difference value between the initial value and the final value of the value ranges of the red, green and blue pigments is not more than 20, and 1, 3, 5, 10 and 20 can be selected; the difference between the starting value and the ending value of red, green and blue can be set to the same value or different values;
intercepting color features of vehicle brand area positions of various types of vehicles from the vehicle head image, comparing the color features with color feature values of brand mark position areas of typical vehicle type collection sample images, and selecting a vehicle brand mark corresponding to the maximum value in all comparison results as a vehicle brand mark feature;
(23) identifying a facial feature code of a vehicle driver, and identifying the facial feature code when judging that a face exists in a vehicle head image through image identification;
(24) identifying the identifiable part of the vehicle number plate, and identifying the vehicle number plate characters at the vehicle number plate part by adopting an image character identification method; the identification method of the vehicle license plate part is to collect sample pictures of the existing vehicle brand and typical vehicle type, mark the position area of the vehicle license plate and perform character identification on the position area of the vehicle license plate;
and 4, grading the historical characteristic data, comparing the obtained vehicle characteristic data with the vehicle characteristic data in the vehicle characteristic historical database to obtain each score, wherein the grading method comprises the following steps:
(41) historical vehicle color feature scores are calculated according to vehicle color feature matching degrees, the vehicle color feature matching degrees are matched by adopting n groups of pixel value group ratios with the largest pixel value group ratio, when the red values, the green values and the blue values of the matched color features are overlapped and the ratio error is within 5%, the matching is successful, the pixel value group ratios are arranged from large to small according to the matching success, the matching item scores are decreased progressively, the weights of the matching item scores can be set according to the sequence from large to small, and the matching item scores of all color value groups are added to obtain the historical vehicle color feature scores;
(42) historical brand mark feature scores, matching with historical vehicle brand mark features according to vehicle brand mark feature data, and referring to a color feature matching mode in 41 in a matching mode;
(43) scoring the facial feature codes of the drivers of the historical vehicles, and comparing the obtained face recognition feature codes in the head images of the vehicles with the facial feature codes of the drivers of the historical vehicles to obtain all vehicles which can be matched with the facial feature codes of the drivers, wherein the facial feature codes of the drivers of the vehicles are full scores;
(44) the historical vehicle license plate scores, the identification result of the vehicle license plate identification part obtained from the 24 items is matched with the historical vehicle license plate, according to the sequence, each character or letter matched successfully obtains a matched score, and the sum of the scores obtained by matching all the characters or letters is the historical vehicle license plate score;
and 5, selecting the result with the highest score as the vehicle identification result, wherein the judgment method of the score is as follows:
multiplying each feature score by the weight to obtain the feature score, adding all the feature scores to obtain a total score, and selecting the highest total score as a vehicle identification result;
the score weights are in the order:
the first weight ratio is: scoring historical vehicle number plates;
the second weight ratio is: historical vehicle color feature scores;
the third weight ratio: historical brand logo feature scores;
the fourth weight ratio: scoring the facial feature codes of the historical vehicle drivers;
the sequence of the weight ratio of the four items can be adjusted;
the ratio of the four weight ratios can be freely adjusted; for example, the weight ratios may be set such that the first weight ratio is 30-50%, the second weight ratio is 20-30%, the third weight ratio is 15-20%, and the fourth weight ratio is 5-15%.
Step 6, storing the current vehicle identification result and the vehicle characteristic identification result, and storing the current vehicle identification result and the vehicle characteristic identification result into a vehicle characteristic data historical database;
and (6) ending.
Example two:
the embodiment provides a vehicle identification system for implementing the vehicle identification method of the first embodiment, including: the system comprises a camera, a vehicle identification server, a vehicle characteristic data historical database and an LED display screen; the camera collects images of the head of the vehicle, the vehicle identification server performs vehicle identification on the images of the head of the vehicle collected by the camera according to the steps 2 to 5 of the first embodiment by matching with a vehicle characteristic data historical database to obtain identification results, and the identification results are displayed on an LED display screen, for example, license plate numbers or related information of the vehicles are displayed.
And (3) implementation:
the embodiment provides a vehicle identification system for implementing the vehicle identification method of the first embodiment, including: the system comprises an image collector, a vehicle identification server, a vehicle characteristic data historical database and a vehicle identification result database; the image collector collects images of the front part of the vehicle, the vehicle identification server is matched with the vehicle characteristic data historical database to carry out vehicle identification on the images of the front part of the vehicle collected by the image collector according to the steps 2 to 5 of the first embodiment to obtain an identification result, and the identification result is stored in the vehicle identification result database.
And (4) implementation:
the embodiment provides a vehicle identification system for implementing the vehicle identification method of the first embodiment, including: the system comprises a camera, a vehicle identification server, a vehicle characteristic data historical database and a loudspeaker; the camera collects images of the front part of the vehicle, the vehicle identification server is matched with the vehicle characteristic data historical database to carry out vehicle identification on the images of the front part of the vehicle collected by the camera according to the steps 2 to 5 of the first embodiment to obtain identification results, and the vehicle number identification results are broadcasted through the loudspeaker.
The above description is only for the preferred embodiment of the present invention, but the scope of the present invention is not limited thereto, and any changes or substitutions that can be easily conceived by those skilled in the art within the technical scope of the present invention are included in the scope of the present invention. Therefore, the protection scope of the present invention shall be subject to the protection scope of the claims.
Claims (10)
1. A vehicle identification method, characterized by comprising:
step 1, obtaining a vehicle head image of an identified vehicle, wherein the horizontal identifiable pixels of the vehicle head image are not less than 800 pixels, and the shooting angle of the vehicle head image is not more than 30 degrees when the front part of the identified vehicle horizontally deviates from the central axis of the vehicle;
step 2, identifying vehicle characteristic data from the vehicle head image obtained in the step 1 through image identification, wherein the identified vehicle characteristic data comprises:
(21) vehicle color characteristics: the proportion of color pixels in a preset color group in the vehicle head image pixels is represented, and the representation is represented by the following format:
RGbn, which is the proportion of pixel value groups in the RGB value range in the whole vehicle head image pixels; in the RGBN value, the R value is a haematochrome value range, and the format is an initial value and a final value; the G value range is a green pigment value range, and the format is an initial value and a final value; the B value range is a blue pigment value range, and the format is an initial value and a final value; n represents the number of groups of pixel value groups in the RGB pixel range; the difference value between the initial value and the final value of the value ranges of the red, green and blue pigments is not more than 20, and 1, 3, 5, 10 and 20 can be selected;
(22) vehicle brand logo features: obtaining the color characteristics of the position area of the vehicle brand mark in the vehicle head image, comparing the color characteristics with the color characteristics of the position area of the brand mark of the collected sample image of the existing typical vehicle type, and selecting the vehicle brand mark corresponding to the maximum value in all comparison results as the vehicle brand mark characteristics;
the color characteristics of the vehicle brand mark position area are represented by the following format:
RGbn, which is the proportion of pixel value groups in the RGB value range in the pixels of the whole vehicle brand mark position area image; in the RGBN value, the R value is a haematochrome value range, and the format is an initial value and a final value; the G value range is a green pigment value range, and the format is an initial value and a final value; the B value range is a blue pigment value range, and the format is an initial value and a final value; n represents the number of groups of pixel value groups in the RGB pixel range; the difference value between the initial value and the final value of the value ranges of the red, green and blue pigments is not more than 20, and 1, 3, 5, 10 and 20 can be selected;
(23) vehicle driver facial feature code: if the driver position in the vehicle head image is judged to be a face, recognizing a face feature code of the driver position as a face feature code of a vehicle driver;
(24) vehicle number plate recognizing section: identifying vehicle number plate characters from the vehicle number plate part in the vehicle head image;
step 3, obtaining all historical vehicle characteristic data from a vehicle characteristic data historical database;
step 4, scoring historical characteristic data: comparing the vehicle characteristic data obtained in the step 2 with the historical vehicle characteristic data obtained in the step 3 to obtain a score of each characteristic comparison, wherein the scoring mode of each score is as follows:
(41) historical vehicle color feature score: calculating vehicle color feature scores according to vehicle color feature matching degrees, wherein the vehicle color feature matching degrees adopt n groups of pixel value group ratios with the largest pixel value group ratio for matching, when the red pigment value, the green pigment value and the blue pigment value of the matched color features are overlapped and the ratio error is within 5%, the matching is successful, the pixel value group ratios which are successfully matched are arranged from large to small, the matching item scores are decreased, the weights of the matching item scores are set from large to small, and the matching item scores of all the pixel value groups are added to obtain historical vehicle color feature scores;
(42) historical vehicle brand signature feature score: matching color features according to the vehicle brand mark features and the historical vehicle brand mark features, wherein the matching color feature mode is the same as the matching mode in the historical vehicle color feature score;
(43) the historical vehicle driver facial feature codes are scored, the obtained vehicle driver facial feature codes are compared with the historical vehicle driver facial feature codes, and if all vehicles which can be matched with the driver facial feature codes are obtained, the driver feature codes of the vehicles are full marks;
(44) the historical vehicle license plate scores, the obtained vehicle license plate identification part is matched with the historical vehicle license plate, a corresponding score is obtained every time one character or letter is successfully matched according to the same direction sequence, and the sum of the scores after all the characters or letters are matched is the historical vehicle license plate score;
and 5, selecting the result with the highest score as a vehicle identification result, and judging the score according to the following modes:
and multiplying each feature comparison score by the corresponding weight to obtain the feature score, adding all the feature scores to obtain a total score, and selecting the result with the highest total score as the vehicle identification result.
2. The vehicle identification method according to claim 1, wherein in the step 5, the order of the weights corresponding to the feature comparison scores is as follows:
the first weight ratio is: scoring historical vehicle number plates;
the second weight ratio is: historical vehicle color feature scores;
the third weight ratio: historical brand logo feature scores;
the fourth weight ratio: historical vehicle driver facial feature code scores.
The first weight proportion is larger than the second weight proportion, the second weight proportion is larger than the third weight proportion, and the third weight proportion is larger than the fourth weight proportion.
3. The vehicle identification method according to claim 1 or 2, characterized by further comprising, after the step 5: and 6, storing the current vehicle identification result and the vehicle characteristic data into a vehicle characteristic data historical database.
4. The vehicle identification method according to claim 1 or 2, wherein in the step 2, the color characteristics of the brand mark position area of the existing typical vehicle type collected sample map are determined by:
collecting a sample map of an existing vehicle brand and a typical vehicle type, marking a brand mark position area in the sample map, and obtaining the color characteristics of the marked brand mark position area in the sample map through image recognition, wherein the color characteristics are represented by the following format:
RGbn, which is the proportion of pixel value groups in the RGB value range in the whole brand mark position area image pixels; in the RGBN value, the R value is a haematochrome value range, and the format is an initial value and a final value; the G value range is a green pigment value range, and the format is (initial value, end value); the B value range is a blue pigment value range, and the format is an initial value and a final value); n represents the number of groups of pixel value groups in the RGB pixel range; the difference between the initial value and the final value of the value ranges of the red, green and blue pigments is not more than 20, and 1, 3, 5, 10 and 20 can be selected.
5. A vehicle identification system for implementing the method of any one of claims 1 to 4, comprising:
the system comprises a shooting device, a vehicle identification server, a vehicle characteristic data historical database and a vehicle identification result output device; wherein the content of the first and second substances,
the shooting device is in communication connection with the vehicle identification server, can acquire a vehicle head image of the identified vehicle and sends the vehicle head image to the vehicle identification server;
the vehicle identification server is respectively in communication connection with the vehicle characteristic data historical database and the vehicle identification result output device, can identify vehicle characteristic data from the vehicle head image obtained in the step 1 through image identification, can obtain all historical vehicle characteristic data from the vehicle characteristic data historical database, and obtains a score of each feature comparison by comparing the obtained vehicle characteristic data with the historical vehicle characteristic data, selects a result with the highest score as a vehicle identification result, and sends the vehicle identification result to the vehicle identification result output device;
and the vehicle identification result output device outputs the vehicle identification result obtained by the vehicle identification server.
6. The vehicle recognition system according to claim 5, wherein the vehicle recognition result output means includes: at least one of a graphic display device and a sound playing device.
7. The vehicle identification system according to claim 5 or 6, wherein the photographing device employs at least one of a camera, a terminal having a camera.
8. The vehicle identification system according to claim 5 or 6, further comprising: the vehicle identification server stores the identification result to the vehicle characteristic data history database.
9. The vehicle identification system of claim 5 or 6, wherein the vehicle characteristic data identified by the vehicle identification server comprises:
(21) vehicle color features, represented in the following format:
RGbn, which is the proportion of pixel value groups in the RGB value range in the whole vehicle head image pixels; in the RGBN value, the R value is a haematochrome value range, and the format is an initial value and a final value; the G value range is a green pigment value range, and the format is an initial value and a final value; the B value range is a blue pigment value range, and the format is an initial value and a final value; n represents the number of groups of pixel value groups in the RGB pixel range; the difference value between the initial value and the final value of the value ranges of the red, green and blue pigments is not more than 20, and 1, 3, 5, 10 and 20 can be selected;
(22) vehicle brand logo features: obtaining the color characteristics of the position area of the vehicle brand mark in the vehicle head image, comparing the color characteristics with the color characteristics of the position area of the brand mark of the collected sample image of the existing typical vehicle type, and selecting the vehicle brand mark corresponding to the maximum value in all comparison results as the vehicle brand mark characteristics;
the color characteristics of the vehicle brand mark position area are represented by the following format:
RGbn, which is the proportion of pixel value groups in the RGB value range in the pixels of the whole vehicle brand mark position area image; in the RGBN value, the R value is a haematochrome value range, and the format is an initial value and a final value; the G value range is a green pigment value range, and the format is an initial value and a final value; the B value range is a blue pigment value range, and the format is an initial value and a final value; n represents the number of groups of pixel value groups in the RGB pixel range; the difference value between the initial value and the final value of the value ranges of the red, green and blue pigments is not more than 20, and 1, 3, 5, 10 and 20 can be selected;
(23) vehicle driver facial feature code: if the driver position in the vehicle head image is judged to be a face, recognizing a face feature code of the driver position as a face feature code of a vehicle driver;
(24) vehicle number plate recognizing section: and identifying vehicle number plate characters from the vehicle number plate part in the vehicle head image.
10. The vehicle identification system of claim 5 or 6, wherein the vehicle identification server compares the obtained vehicle characteristic data with historical vehicle characteristic data to obtain a score for each characteristic comparison score, and comprises:
(41) historical vehicle color feature score: calculating vehicle color feature scores according to vehicle color feature matching degrees, wherein the vehicle color feature matching degrees adopt n groups of pixel value group ratios with the largest color pixel number ratio for matching, when the red value, the green value and the blue value of the matched color features are overlapped and the ratio error is within 5%, the matching is successful, the pixel value group ratios which are successfully matched are arranged from large to small, the matching scores are decreased, the weights are set according to the sequence from large to small for each matching score, and the matching scores of all color value groups are added to obtain historical vehicle color feature scores;
(42) historical vehicle brand signature feature score: matching color features according to the vehicle brand mark features and the historical vehicle brand mark features, wherein the matching color feature mode is the same as the matching mode in the historical vehicle color feature score;
(43) the historical vehicle driver facial feature codes are scored, the obtained vehicle driver facial feature codes are compared with the historical vehicle driver facial feature codes, and if all vehicles which can be matched with the driver facial feature codes are obtained, the driver feature codes of the vehicles are full marks;
(44) and scoring the historical vehicle license plate, matching the obtained vehicle license plate recognition part with the historical vehicle license plate, obtaining a corresponding score for each character or letter matched successfully according to the same direction sequence, wherein the sum of the scores after all the characters or letters are matched is the score of the historical vehicle license plate.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110613489.XA CN113362612A (en) | 2021-06-02 | 2021-06-02 | Vehicle identification method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110613489.XA CN113362612A (en) | 2021-06-02 | 2021-06-02 | Vehicle identification method and system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113362612A true CN113362612A (en) | 2021-09-07 |
Family
ID=77531231
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110613489.XA Pending CN113362612A (en) | 2021-06-02 | 2021-06-02 | Vehicle identification method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113362612A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114495545A (en) * | 2022-01-28 | 2022-05-13 | 常州海蓝利科物联网技术有限公司 | Vehicle control system and method |
Citations (16)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102663892A (en) * | 2012-05-29 | 2012-09-12 | 四川川大智胜软件股份有限公司 | Method for correcting discoloration and enlarging of red light in night red-light-running vehicle picture |
| CN103150904A (en) * | 2013-02-05 | 2013-06-12 | 中山大学 | Bayonet vehicle image identification method based on image features |
| CN103325114A (en) * | 2013-06-13 | 2013-09-25 | 同济大学 | Target vehicle matching method based on improved vision attention model |
| CN103678558A (en) * | 2013-12-06 | 2014-03-26 | 中科联合自动化科技无锡有限公司 | Suspicion vehicle search method based on sift characteristic |
| CN104715239A (en) * | 2015-03-12 | 2015-06-17 | 哈尔滨工程大学 | Vehicle color identification method based on defogging processing and weight blocking |
| CN105320923A (en) * | 2014-08-05 | 2016-02-10 | 北京大学 | Vehicle type recognition method and apparatus |
| CN107169992A (en) * | 2017-05-11 | 2017-09-15 | 南宁市正祥科技有限公司 | A kind of traffic video moving target detecting method |
| CN107633687A (en) * | 2017-09-08 | 2018-01-26 | 绵阳西真科技有限公司 | A kind of vehicle identification method and system for parking lot |
| CN107808519A (en) * | 2016-08-25 | 2018-03-16 | 上海瑞警科技有限公司 | A kind of multiple features vehicle match method |
| CN109508395A (en) * | 2018-09-26 | 2019-03-22 | 安徽四创电子股份有限公司 | A method of the intelligence based on vehicle retrieval is combined related cases |
| CN109726701A (en) * | 2019-01-07 | 2019-05-07 | 福建睿思特科技股份有限公司 | Vehicle identification method and system |
| CN110491133A (en) * | 2019-08-08 | 2019-11-22 | 横琴善泊投资管理有限公司 | A kind of information of vehicles correction system and method based on confidence level |
| CN111078927A (en) * | 2019-12-19 | 2020-04-28 | 罗普特科技集团股份有限公司 | Method, device and storage medium for identifying driver identity based on family tree data |
| CN111275984A (en) * | 2020-02-20 | 2020-06-12 | 三一重工股份有限公司 | Vehicle detection method and device and server |
| CN112164229A (en) * | 2020-09-28 | 2021-01-01 | 广西信路威科技发展有限公司 | Vehicle type recognition matching system and method based on vehicle multidimensional characteristics |
| CN112270309A (en) * | 2020-11-20 | 2021-01-26 | 罗普特科技集团股份有限公司 | Vehicle access point equipment snapshot quality evaluation method and device and readable medium |
-
2021
- 2021-06-02 CN CN202110613489.XA patent/CN113362612A/en active Pending
Patent Citations (16)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102663892A (en) * | 2012-05-29 | 2012-09-12 | 四川川大智胜软件股份有限公司 | Method for correcting discoloration and enlarging of red light in night red-light-running vehicle picture |
| CN103150904A (en) * | 2013-02-05 | 2013-06-12 | 中山大学 | Bayonet vehicle image identification method based on image features |
| CN103325114A (en) * | 2013-06-13 | 2013-09-25 | 同济大学 | Target vehicle matching method based on improved vision attention model |
| CN103678558A (en) * | 2013-12-06 | 2014-03-26 | 中科联合自动化科技无锡有限公司 | Suspicion vehicle search method based on sift characteristic |
| CN105320923A (en) * | 2014-08-05 | 2016-02-10 | 北京大学 | Vehicle type recognition method and apparatus |
| CN104715239A (en) * | 2015-03-12 | 2015-06-17 | 哈尔滨工程大学 | Vehicle color identification method based on defogging processing and weight blocking |
| CN107808519A (en) * | 2016-08-25 | 2018-03-16 | 上海瑞警科技有限公司 | A kind of multiple features vehicle match method |
| CN107169992A (en) * | 2017-05-11 | 2017-09-15 | 南宁市正祥科技有限公司 | A kind of traffic video moving target detecting method |
| CN107633687A (en) * | 2017-09-08 | 2018-01-26 | 绵阳西真科技有限公司 | A kind of vehicle identification method and system for parking lot |
| CN109508395A (en) * | 2018-09-26 | 2019-03-22 | 安徽四创电子股份有限公司 | A method of the intelligence based on vehicle retrieval is combined related cases |
| CN109726701A (en) * | 2019-01-07 | 2019-05-07 | 福建睿思特科技股份有限公司 | Vehicle identification method and system |
| CN110491133A (en) * | 2019-08-08 | 2019-11-22 | 横琴善泊投资管理有限公司 | A kind of information of vehicles correction system and method based on confidence level |
| CN111078927A (en) * | 2019-12-19 | 2020-04-28 | 罗普特科技集团股份有限公司 | Method, device and storage medium for identifying driver identity based on family tree data |
| CN111275984A (en) * | 2020-02-20 | 2020-06-12 | 三一重工股份有限公司 | Vehicle detection method and device and server |
| CN112164229A (en) * | 2020-09-28 | 2021-01-01 | 广西信路威科技发展有限公司 | Vehicle type recognition matching system and method based on vehicle multidimensional characteristics |
| CN112270309A (en) * | 2020-11-20 | 2021-01-26 | 罗普特科技集团股份有限公司 | Vehicle access point equipment snapshot quality evaluation method and device and readable medium |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114495545A (en) * | 2022-01-28 | 2022-05-13 | 常州海蓝利科物联网技术有限公司 | Vehicle control system and method |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108364010B (en) | License plate recognition method, device, equipment and computer readable storage medium | |
| CN111488875B (en) | Vehicle insurance claim settlement loss checking method and device based on image recognition and electronic equipment | |
| US8391559B2 (en) | Method and system for image identification and identification result output | |
| US8059868B2 (en) | License plate recognition apparatus, license plate recognition method, and computer-readable storage medium | |
| CN105046196B (en) | Front truck information of vehicles structuring output method based on concatenated convolutional neutral net | |
| KR20150039367A (en) | Licence plate recognition system | |
| JP5830338B2 (en) | Form recognition method and form recognition apparatus | |
| CN103544484A (en) | Traffic sign identification method and system based on SURF | |
| CN105139011B (en) | A kind of vehicle identification method and device based on mark object image | |
| CN104463134B (en) | A kind of detection method of license plate and system | |
| CN111832388B (en) | Method and system for detecting and identifying traffic sign in vehicle running | |
| CN112115939A (en) | Vehicle license plate recognition method and device | |
| CN106874901A (en) | A kind of driving license recognition methods and device | |
| CN113362612A (en) | Vehicle identification method and system | |
| CN108182691A (en) | Identify the method, apparatus and vehicle of speed(-)limit sign | |
| CN110674821B (en) | License plate recognition method for non-motor vehicle | |
| CN117636359A (en) | Method, device, processor and computer readable storage medium for implementing character recognition and extraction processing for seal face | |
| CN111860477A (en) | Vehicle information verification method and system, terminal, and computer-readable storage medium | |
| CN114187253A (en) | Circuit board part installation detection method | |
| Chowdhury et al. | An adaptive technique for computer vision based vehicles license plate detection system | |
| CN110569801B (en) | Identification method for key content of driving license | |
| CN110969135B (en) | Vehicle logo recognition method in natural scene | |
| CN110766001B (en) | Bank card number positioning and end-to-end identification method based on CNN and RNN | |
| CN109558872B (en) | Vehicle color identification method | |
| CN110046618B (en) | License plate recognition method based on machine learning and maximum extremum stable region |
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 | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20210907 |