CN109934161B - Vehicle identification and detection method and system based on convolutional neural network - Google Patents
Vehicle identification and detection method and system based on convolutional neural network Download PDFInfo
- Publication number
- CN109934161B CN109934161B CN201910182868.0A CN201910182868A CN109934161B CN 109934161 B CN109934161 B CN 109934161B CN 201910182868 A CN201910182868 A CN 201910182868A CN 109934161 B CN109934161 B CN 109934161B
- Authority
- CN
- China
- Prior art keywords
- vehicle
- images
- identified
- vehicles
- monitoring
- 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.)
- Active
Links
Images
Classifications
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02T—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO TRANSPORTATION
- Y02T10/00—Road transport of goods or passengers
- Y02T10/10—Internal combustion engine [ICE] based vehicles
- Y02T10/40—Engine management systems
Landscapes
- Traffic Control Systems (AREA)
- Alarm Systems (AREA)
Abstract
The invention relates to a vehicle identification and detection method and system based on a convolutional neural network, which are characterized by comprising the following steps: extracting a vehicle picture sample and marking; carrying out region segmentation and category analysis training on the marked picture sample; extracting a group of random continuous images to be identified in the video to be identified; predicting the positions and types of vehicles in all images to be recognized; outputting a motion state of the vehicle; the invention adopts the vehicle identification system to carry out intelligent and automatic management on related vehicles, controls and manages urban traffic by adopting modern technical means, controls the running state of each vehicle in real time, can conveniently realize vehicle dispatching, can guide the dangerous vehicle to track and treat when danger occurs, and lays a solid foundation for timely dredging and efficient monitoring by management departments.
Description
Technical Field
The invention relates to the technical field of vehicle identification and management, in particular to a vehicle identification and detection method and system based on a convolutional neural network.
Background
With the rapid development of social economy, the number of automobiles in main cities in each country is increased, and the illegal parking of the automobiles is one of the major causes of traffic jam, so that each country is definitely regulated by corresponding laws and regulations, the parking is forbidden at specific places, places and roads, and at present, the supervision of illegal parking behaviors by traffic departments mainly adopts a manual patrol mode, so that the supervision of illegal parking by the manual patrol mode requires a large amount of manpower and material resources, and few equipment can simultaneously meet the requirements of real-time performance, accuracy and effectiveness.
In addition, in recent years, the number of special vehicles such as tank trucks, hazardous chemical transport vehicles, mud-head vehicles, police cars, etc. has increased, and in order to determine the position of a traveling vehicle, a method of positioning by using an electric wave signal from GPS (Global Positioning System: global positioning system) has been widely used. However, the accuracy of positioning the vehicle by using the GPS has an error of about several tens of meters, and it is difficult to perform detailed position determination with higher accuracy, so that the conventional special vehicle management mode has difficulty in meeting actual requirements, has low supervision efficiency, and has potential safety hazards.
The traffic information acquisition based on video image processing is widely paid attention to at home and abroad as an important detection technology, the video detection technology is rapidly developed along with the development of society and economy and the development of scientific technology, video detection products are in a high-definition development stage after undergoing two important development stages of simulation and digital, high-definition video detection products are in the market at present, a traffic video detection sensor obtains traffic scene images through video acquisition equipment above a road, and scene image information is automatically analyzed and processed by utilizing technologies such as computer image processing, artificial intelligence and pattern recognition, so that the traffic information is obtained. The non-contact traffic information acquisition equipment can be used for installing, debugging and maintaining the equipment without affecting the running condition of the vehicle, a closed road section is not needed, and meanwhile, the video detection sensor can be used for detecting a plurality of lanes simultaneously and monitoring traffic in a wide-area scene, and has the characteristics of low cost, comprehensive and visual information, easiness in maintenance and installation and the like, so that the non-contact traffic information acquisition equipment has a higher application prospect in an intelligent traffic system.
Disclosure of Invention
The invention aims to solve the technical problem of overcoming the defects in the prior art and providing a vehicle identification and detection method and system based on a convolutional neural network.
The invention is realized by the following technical scheme:
the vehicle identification and detection method based on the convolutional neural network is characterized by comprising the following steps of:
a. extracting a group of picture samples of specific forms of different types of vehicles, and marking all types of vehicles in the picture samples;
b. performing region segmentation and category analysis training on the marked picture sample by using a mask-rcnn;
c. establishing communication connection with a video monitoring end, and extracting a group of random continuous images to be identified in the video to be identified;
d. predicting the positions and types of vehicles in all images to be recognized through mask-rcnn semantic segmentation;
e. tracking and outputting the motion state of the vehicle through the motion of the video;
f. binding the motion state with the vehicle monitoring service logic, and outputting a monitoring result and an instruction.
According to the above technical solution, preferably, the image to be identified is a group of images continuously selected in a time period of random extraction in the video to be identified.
According to the above technical solution, preferably, step e includes: tracking all vehicle positions in the images to be identified of the adjacent frames through an object tracking algorithm; and outputting the motion state of the vehicle according to the tracking condition of the vehicle.
According to the above technical solution, preferably, step f includes: and when the motion state of the vehicle in the specific area is stationary, sending a reminding instruction to the monitoring end.
According to the above technical solution, preferably, step f includes: and when the stationary time of the vehicle exceeds the preset duration, sending a reminding instruction to the monitoring end.
A convolutional neural network-based vehicle identification and detection system, comprising: the marking unit is used for extracting a group of picture samples of specific forms of different types of vehicles and marking all types of vehicles in the picture samples; the training unit is used for carrying out region segmentation and category analysis training on the marked picture sample by using a mask-rcnn; the extraction unit is used for establishing communication connection with the video monitoring end and extracting a group of random continuous images to be identified in the video to be identified; the vehicle information identification unit is used for predicting the positions and types of vehicles in all the images to be identified through mask-rcnn semantic segmentation; the vehicle displacement recognition unit is used for tracking and outputting the motion state of the vehicle through the motion of the video; and the monitoring unit is used for binding the motion state with the vehicle monitoring service logic and outputting a monitoring result and an instruction.
According to the above-described aspect, preferably, the vehicle displacement identification unit includes: the tracking module is used for tracking all vehicle positions in the images to be identified of the adjacent frames through an object tracking algorithm; and the output module is used for outputting the motion state of the vehicle according to the tracking condition of the vehicle.
According to the above technical solution, preferably, the monitoring unit includes: the first judging module is used for sending a reminding instruction to the monitoring end when the motion state of the vehicle in the specific area is stationary.
According to the above technical solution, preferably, the monitoring unit includes: and the second judging module is used for sending a reminding instruction to the monitoring end when the stationary time of the vehicle exceeds the preset duration.
The beneficial effects of the invention are as follows:
the method is characterized in that images recorded by a video monitoring end are extracted, video clips are identified and analyzed, the motion state of a vehicle is identified through motion tracking of the video, information instructions are transmitted to a vehicle monitoring management center through the Internet for the vehicle state meeting specific conditions, a vehicle identification system is adopted for intelligent and automatic management of related vehicles, the running state of each vehicle is controlled in real time for controlling and managing urban traffic by adopting modern technical means, vehicle scheduling can be conveniently realized, and when danger occurs, the dangerous vehicle can be guided to track and treat, and a solid foundation is laid for timely dredging and efficient monitoring by a management department.
Drawings
Fig. 1 is a schematic diagram of the operation of the present invention.
Detailed Description
The present invention will be described in further detail below with reference to the drawings and preferred embodiments, so that those skilled in the art can better understand the technical solutions of the present invention.
As shown in the figure, the invention discloses a vehicle identification and detection method based on a convolutional neural network, which is characterized by comprising the following steps: a. extracting a group of picture samples of different types of vehicle specific forms, marking all types of vehicles in the picture samples, finely marking the contours of all vehicles in the intercepted picture samples containing various vehicle specific forms by using a VIA image marking algorithm frame, forming contours surrounded by a plurality of closed polygons, marking the names of the vehicle types, and exporting marked information into json files; b. performing region segmentation and category analysis training on the marked picture sample by using a mask-rcnn, wherein a mask-rcnn algorithm under a tensorflow frame is used for training json file samples in the example; c. the method comprises the steps that communication connection is established with a video monitoring end, a group of random continuous images to be identified in videos to be identified are extracted, the video monitoring end in the embodiment can be a monitoring camera used for monitoring whether a common vehicle invades a specific area or not, and the video monitoring end can also be a video shot by a satellite and used for monitoring the motion state of the special vehicle in different environments; d. predicting the positions and types of vehicles in all images to be recognized through mask-rcnn semantic segmentation; e. tracking and outputting the motion state of the vehicle through the motion of the video; f. binding the motion state with the vehicle monitoring service logic, and outputting a monitoring result and an instruction. The method is characterized in that images recorded by a video monitoring end are extracted, video clips are identified and analyzed, the motion state of a vehicle is identified through motion tracking of the video, information instructions are transmitted to a vehicle monitoring management center through the Internet for the vehicle state meeting specific conditions, a vehicle identification system is adopted for intelligent and automatic management of related vehicles, the running state of each vehicle is controlled in real time for controlling and managing urban traffic by adopting modern technical means, vehicle scheduling can be conveniently realized, and when danger occurs, the dangerous vehicle can be guided to track and treat, and a solid foundation is laid for timely dredging and efficient monitoring by a management department.
According to the above embodiment, preferably, the image to be identified is a group of images continuously selected in a randomly extracted time period in the video to be identified, in this example, the video to be identified is imported by using an image algorithm framework, a certain time period is extracted from the video, the extracted time period is related to the operation speed and the observation time, and the group of images can be selected as the image to be identified randomly and continuously, but not excessively short.
According to the above embodiment, preferably, the step e includes: tracking all vehicle positions in images to be identified of adjacent frames through an object tracking algorithm, starting from a first frame in the images to be identified, observing all vehicle positions of the images of the adjacent frames, calculating the mass center of each vehicle outline by using a matrix algorithm, sequentially searching by taking the mass center of each vehicle of the first image as the center of a circle and taking preset pixels as the radius, checking the displacement condition of each vehicle in the next frame, judging whether the shape difference between the object and the object of which the mass center is positioned is in a certain range, if so, considering the current object as the object of which the mass center of the previous image is positioned, and otherwise, considering the current object as a different type of vehicle; and outputting the motion state of the vehicle according to the tracking condition of the vehicle, and considering the vehicle to be in a stationary state if the mass center of the same vehicle does not move within a certain time.
According to the above embodiment, preferably, the step f includes: when the vehicle is in a static state in a specific area, a reminding instruction is sent to the monitoring end, and when the vehicle is in a static state in a forbidden and stopped position, the system sends the reminding instruction to the traffic management center, so that a traffic manager can quickly judge the motion state of the vehicle, the intelligent level of a road monitoring video can be improved, and a timely and effective accident handling means and basis are provided for the traffic manager.
According to the above embodiment, preferably, the step f includes: when the resting time of the vehicle exceeds the preset time, a reminding instruction is sent to the monitoring end, a reasonable vehicle resting time alarm threshold is set, and when the resting time of the special vehicle in certain specific environments exceeds the alarm threshold, the system sends the reminding instruction to the monitoring end, so that the running state of each vehicle can be controlled in real time, and when the danger occurs, the dangerous vehicle can be guided to track and treat, and a solid foundation is laid for timely dredging and efficient monitoring by the management department.
The invention also discloses a vehicle identification and detection system based on the convolutional neural network, which is characterized by comprising the following steps: the marking unit is used for extracting a group of picture samples of specific forms of different types of vehicles and marking all types of vehicles in the picture samples; the training unit is used for carrying out region segmentation and category analysis training on the marked picture sample by using a mask-rcnn; the extraction unit is used for establishing communication connection with the video monitoring end and extracting a group of random continuous images to be identified in the video to be identified; the vehicle information identification unit is used for predicting the positions and types of vehicles in all the images to be identified through mask-rcnn semantic segmentation; the vehicle displacement recognition unit is used for tracking and outputting the motion state of the vehicle through the motion of the video; and the monitoring unit is used for binding the motion state with the vehicle monitoring service logic and outputting a monitoring result and an instruction.
According to the above embodiment, preferably, the vehicle displacement identification unit includes: the tracking module is used for tracking all vehicle positions in the images to be identified of the adjacent frames through an object tracking algorithm; and the output module is used for outputting the motion state of the vehicle according to the tracking condition of the vehicle.
According to the above embodiment, preferably, the monitoring unit includes: the first judging module is used for sending a reminding instruction to the monitoring end when the motion state of the vehicle in the specific area is stationary.
According to the above embodiment, preferably, the monitoring unit includes: and the second judging module is used for sending a reminding instruction to the monitoring end when the stationary time of the vehicle exceeds the preset duration.
The method is characterized in that images recorded by a video monitoring end are extracted, video clips are identified and analyzed, the motion state of a vehicle is identified through motion tracking of the video, information instructions are transmitted to a vehicle monitoring management center through the Internet for the vehicle state meeting specific conditions, a vehicle identification system is adopted for intelligent and automatic management of related vehicles, the running state of each vehicle is controlled in real time for controlling and managing urban traffic by adopting modern technical means, vehicle scheduling can be conveniently realized, and when danger occurs, the dangerous vehicle can be guided to track and treat, and a solid foundation is laid for timely dredging and efficient monitoring by a management department.
The foregoing is merely a preferred embodiment of the present invention and it should be noted that modifications and adaptations to those skilled in the art may be made without departing from the principles of the present invention, which are intended to be comprehended within the scope of the present invention.
Claims (3)
1. The vehicle identification and detection method based on the convolutional neural network is characterized by comprising the following steps of:
a. extracting a group of picture samples of specific forms of different types of vehicles, and marking all types of vehicles in the picture samples;
b. performing region segmentation and category analysis training on the marked picture sample by using a mask-rcnn;
c. establishing communication connection with a video monitoring end, and extracting a group of random continuous images to be identified in the video to be identified;
d. predicting the positions and types of vehicles in all images to be recognized through mask-rcnn semantic segmentation;
e. tracking all vehicle positions in images to be identified of adjacent frames through an object tracking algorithm, starting from a first frame in the images to be identified, observing all vehicle positions of the images of the adjacent frames, calculating the mass center of each vehicle outline by using a matrix algorithm, sequentially searching by taking the mass center of each vehicle of the first image as the center of a circle and taking preset pixels as the radius, checking the displacement condition of each vehicle in the next frame, judging whether the shape difference between the object and the object of which the mass center is positioned is in a preset range, if so, considering the current object as the object of which the mass center of the previous image is positioned, and otherwise, considering the current object as a different type of vehicle; outputting the motion state of the vehicle according to the tracking condition of the vehicle, and if the mass center of the same vehicle does not move within the preset time, considering the vehicle to be in a stationary state;
f. binding the motion state with vehicle monitoring service logic, outputting a monitoring result and an instruction, wherein when the stationary time of the vehicle exceeds a preset time length, a reminding instruction is sent to a monitoring end, a reasonable vehicle stationary time length alarm threshold value is set, and when the stationary time of the vehicle in certain specific environments exceeds the alarm threshold value, the system sends the reminding instruction to the monitoring end.
2. The method for identifying and detecting vehicles based on convolutional neural network according to claim 1, wherein the images to be identified are a group of images continuously selected in a time period of random extraction in the video to be identified.
3. A convolutional neural network-based vehicle identification and detection system, comprising:
the marking unit is used for extracting a group of picture samples of specific forms of different types of vehicles and marking all types of vehicles in the picture samples;
the training unit is used for carrying out region segmentation and category analysis training on the marked picture sample by using a mask-rcnn;
the extraction unit is used for establishing communication connection with the video monitoring end and extracting a group of random continuous images to be identified in the video to be identified;
the vehicle information identification unit is used for predicting the positions and types of vehicles in all the images to be identified through mask-rcnn semantic segmentation;
the vehicle displacement recognition unit is used for tracking all vehicle positions in the images to be recognized of the adjacent frames through an object tracking algorithm, observing all vehicle positions of the images of the adjacent frames from the first frame in the images to be recognized, calculating the mass center of each vehicle contour by using a matrix algorithm, sequentially searching by taking the mass center of each vehicle of the first image as the center of a circle and taking preset pixels as the radius, checking each vehicle displacement condition in the next frame, judging whether the shape difference between the object and the object of which the mass center is positioned is in a preset range, if so, considering the current object as the object of which the mass center of the last image is positioned to generate displacement, otherwise, considering the current object as a different type of vehicle; outputting the motion state of the vehicle according to the tracking condition of the vehicle, and if the mass center of the same vehicle does not move within the preset time, considering the vehicle to be in a stationary state;
the monitoring unit is used for binding the motion state with the vehicle monitoring business logic and outputting a monitoring result and an instruction, wherein when the stationary time of the vehicle exceeds the preset time length, a reminding instruction is sent to the monitoring end, a reasonable vehicle stationary time length alarm threshold value is set, and when the residence time of the vehicle in certain specific environments exceeds the alarm threshold value, the system sends the reminding instruction to the monitoring end.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910182868.0A CN109934161B (en) | 2019-03-12 | 2019-03-12 | Vehicle identification and detection method and system based on convolutional neural network |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910182868.0A CN109934161B (en) | 2019-03-12 | 2019-03-12 | Vehicle identification and detection method and system based on convolutional neural network |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109934161A CN109934161A (en) | 2019-06-25 |
| CN109934161B true CN109934161B (en) | 2023-04-28 |
Family
ID=66986885
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910182868.0A Active CN109934161B (en) | 2019-03-12 | 2019-03-12 | Vehicle identification and detection method and system based on convolutional neural network |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109934161B (en) |
Families Citing this family (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112180913A (en) * | 2020-09-01 | 2021-01-05 | 芜湖酷哇机器人产业技术研究院有限公司 | Special vehicle identification method |
| CN112686923A (en) * | 2020-12-31 | 2021-04-20 | 浙江航天恒嘉数据科技有限公司 | Target tracking method and system based on double-stage convolutional neural network |
| CN113469158B (en) * | 2021-09-06 | 2021-11-19 | 智广海联(天津)大数据技术有限公司 | Method and system for identifying illegal hazardous chemical substance transport vehicle based on convolutional neural network |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101968886A (en) * | 2010-09-09 | 2011-02-09 | 西安电子科技大学 | Centroid tracking framework based particle filter and mean shift cell tracking method |
| CN103617410A (en) * | 2013-08-30 | 2014-03-05 | 重庆大学 | Highway tunnel parking detection method based on video detection technology |
| CN104070525A (en) * | 2014-06-18 | 2014-10-01 | 大连大学 | Space manipulator continuous trajectory tracking method |
| CN104282020A (en) * | 2014-09-22 | 2015-01-14 | 中海网络科技股份有限公司 | Vehicle speed detection method based on target motion track |
| CN104615142A (en) * | 2014-12-19 | 2015-05-13 | 重庆大学 | Flight controller for civil small UAV (Unmanned Aerial Vehicle) |
| CN109300165A (en) * | 2018-09-14 | 2019-02-01 | 南京邮电大学 | A kind of novel target tracking localization method based on pixel characteristic |
Family Cites Families (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109145769A (en) * | 2018-08-01 | 2019-01-04 | 辽宁工业大学 | The target detection network design method of blending image segmentation feature |
| CN108710875B (en) * | 2018-09-11 | 2019-01-08 | 湖南鲲鹏智汇无人机技术有限公司 | A kind of take photo by plane road vehicle method of counting and device based on deep learning |
| CN109359538B (en) * | 2018-09-14 | 2020-07-28 | 广州杰赛科技股份有限公司 | Training method of convolutional neural network, gesture recognition method, device and equipment |
-
2019
- 2019-03-12 CN CN201910182868.0A patent/CN109934161B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101968886A (en) * | 2010-09-09 | 2011-02-09 | 西安电子科技大学 | Centroid tracking framework based particle filter and mean shift cell tracking method |
| CN103617410A (en) * | 2013-08-30 | 2014-03-05 | 重庆大学 | Highway tunnel parking detection method based on video detection technology |
| CN104070525A (en) * | 2014-06-18 | 2014-10-01 | 大连大学 | Space manipulator continuous trajectory tracking method |
| CN104282020A (en) * | 2014-09-22 | 2015-01-14 | 中海网络科技股份有限公司 | Vehicle speed detection method based on target motion track |
| CN104615142A (en) * | 2014-12-19 | 2015-05-13 | 重庆大学 | Flight controller for civil small UAV (Unmanned Aerial Vehicle) |
| CN109300165A (en) * | 2018-09-14 | 2019-02-01 | 南京邮电大学 | A kind of novel target tracking localization method based on pixel characteristic |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109934161A (en) | 2019-06-25 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Tian et al. | An automatic car accident detection method based on cooperative vehicle infrastructure systems | |
| CN107782564B (en) | Automatic driving vehicle evaluation system and method | |
| CN107843440B (en) | System and method for testing performance of automatic driving vehicle | |
| CN109934161B (en) | Vehicle identification and detection method and system based on convolutional neural network | |
| CN105160899B (en) | A kind of illegal managing device of Internet of Things intelligent transportation | |
| CN111833598B (en) | Automatic traffic incident monitoring method and system for unmanned aerial vehicle on highway | |
| CN109782364B (en) | Traffic sign board missing detection method based on machine vision | |
| CN107067730B (en) | Network appointment vehicle-man-vehicle inconsistency monitoring method based on bayonet equipment | |
| CN109815912B (en) | Highway safety inspection system based on artificial intelligence | |
| CN103258430A (en) | Road traveling time calculating and traffic road condition judging method and road traveling time calculating and traffic road condition judging device | |
| CN109993138A (en) | A kind of car plate detection and recognition methods and device | |
| CN108256554A (en) | Vehicle reverse stopping judgment method, server and system based on deep learning | |
| CN112447041B (en) | Method and device for identifying operation behavior of vehicle and computing equipment | |
| CN105187790B (en) | Method, device and system for monitoring working state of vehicle-mounted terminal | |
| CN112381014A (en) | Illegal parking vehicle detection and management method and system based on urban road | |
| CN113487877A (en) | Road vehicle illegal parking monitoring method | |
| CN114387785A (en) | Safety management and control method and system based on intelligent highway and storable medium | |
| CN110880243B (en) | Road illegal parking management method based on high-order video roadside parking charging equipment | |
| CN111127882A (en) | Tourist attraction parking lot coming vehicle number prediction method based on big data | |
| KR102562757B1 (en) | Prediction and recognition method of road marking information and road maintenance method | |
| CN107958591A (en) | A kind of roadside parking management system based on street lamp | |
| CN111427063B (en) | Mobile device traffic control method, device, equipment, system and medium | |
| CN114724356B (en) | GIS expressway accident early warning method and system based on meteorological data integration | |
| CN113593253A (en) | Method and device for monitoring red light running of vehicle | |
| CN112633163A (en) | Detection method for realizing illegal operation vehicle detection based on machine learning algorithm |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |