CN103473925A - Verification method of road vehicle detection system - Google Patents

Verification method of road vehicle detection system Download PDF

Info

Publication number
CN103473925A
CN103473925A CN2013103827685A CN201310382768A CN103473925A CN 103473925 A CN103473925 A CN 103473925A CN 2013103827685 A CN2013103827685 A CN 2013103827685A CN 201310382768 A CN201310382768 A CN 201310382768A CN 103473925 A CN103473925 A CN 103473925A
Authority
CN
China
Prior art keywords
frame
barrier
detection system
undetected
vehicle detection
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Granted
Application number
CN2013103827685A
Other languages
Chinese (zh)
Other versions
CN103473925B (en
Inventor
周智恒
黄伟烈
杜孙正
张文婷
陈妙薇
欧晓文
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
HUIZHOU DESAY INDUSTRY DEVELOPMENT Co Ltd
Original Assignee
HUIZHOU DESAY INDUSTRY DEVELOPMENT Co Ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by HUIZHOU DESAY INDUSTRY DEVELOPMENT Co Ltd filed Critical HUIZHOU DESAY INDUSTRY DEVELOPMENT Co Ltd
Priority to CN201310382768.5A priority Critical patent/CN103473925B/en
Publication of CN103473925A publication Critical patent/CN103473925A/en
Application granted granted Critical
Publication of CN103473925B publication Critical patent/CN103473925B/en
Expired - Fee Related legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Landscapes

  • Traffic Control Systems (AREA)
  • Image Analysis (AREA)
  • Image Processing (AREA)

Abstract

The invention discloses a verification method of a road vehicle detection system. The road vehicle detection system is verified by a standard training video, so that the detection rate of the road vehicle detection system can be judged, all the follow-up detection indexes are convenient to calculate, and the detection quality of the vehicle detection system can be reflected in a test environment. The verification method of the road vehicle detection system is suitable for both single frame images and multiframe images.

Description

A kind of verification method of road vehicle detection system
Technical field
The present invention relates to image and process and the machine vision technique field, relate in particular to a kind of verification method of road vehicle detection system.
Background technology
The today of extending in all direction in the Modern Traffic transportation, intelligent transportation system is arisen at the historic moment.Wherein, utilize video frequency pick-up head collection vehicle the place ahead traffic information that travels, the technology of carrying out vehicle detection in video image is a study hotspot of traffic and transport field.Vehicle detection is in conjunction with real-time traffic parameter and digital image processing techniques, for the driver provides the accurate location of area-of-interest vehicle, environmental aspect and the threat information of feedback vehicle front.The effect of vehicle detection has determined the performance height of whole system, is the assessment directly perceived that can potential security threat that the vehicle to travelling on road faces play real monitoring and early warning.
In recent years, the various vehicle detecting algorithms of academia emerge in an endless stream.Judge whether a kind of detection algorithm is practical in detection system, and standard should comprise:
Whether the barrier that 1) can identify in time anterior position is vehicle, accurately locks the position of vehicle;
2) all target vehicles of area-of-interest are all demarcated out and statistics, do not lost leakage and catch;
3) the algorithm process information rate is fast, and calculated amount is less, can requirement of real time.
The standard of above assessment vehicle detection, just related to the problem of verification and measurement ratio.Any one vehicle detecting system, except the deficiency that core algorithm itself exists, the complicacy of external environment factor and uncertainty all can make testing result have error, as undetected as vehicle, and flase drops etc. are all inevitable.
The verification and measurement ratio of vehicle detecting system, concern reliability and the validity of system monitoring, is the important statistical indicator of checking system performance.In general, for comparing the effect of detection algorithm, the vehicle fleet size that needs statistic algorithm to detect, statistics is divided into mark and unlabelled.The vehicle target that the explanation of mark is checked through by algorithm, at these in the target of mark, have correct detection, and what detect is vehicle, also has the flase drop phenomenon.Flase drop is that the barrier of other non-vehicles is also identified and marks, and this type of phenomenon is false.Unmarked part, be not detected for the vehicle in target zone, and this situation is defined as undetected.
For the vehicle travelled on road, undetected phenomenon can be brought larger potential safety hazard and threat to the driver, should make system reduce as far as possible loss and even eliminate.Although, and flase drop can not bring significant threat, can increase the overall overhead of system, affect to a certain extent processing speed and the real-time of system, also answer reduce.Just current, the indexs such as statistics verification and measurement ratio are all undertaken by handmarking's method before and after the detection algorithm operation, inefficiency.In the time will adding up multiple image, workload is large, and also may there be mistake in people's number number.And various detection algorithms are devoted to study the process of vehicle identification, how, aspect science calculating verification and measurement ratio method, be still blank.
Summary of the invention
On indicator-specific statistics problem based on present vehicle detection, for the quality of Scientific evaluation vehicle detecting system, but the present invention proposes the verification method of the road vehicle detection system of a kind of accurate statistics loss, false drop rate and vehicle detection rate.
A kind of verification method of road vehicle detection system, it comprises the following steps:
One standard exercise video is provided, and in this standard exercise video, the number of barrier is that N(N is integer), the central point of the default demarcation frame of all barriers is followed successively by
Figure 281830DEST_PATH_IMAGE001
, and the default average gray of demarcating in frame is respectively
Figure 787898DEST_PATH_IMAGE002
, ;
Utilize described road vehicle detection system to be detected described standard exercise video, and obtain its testing result data from this system, described testing result data comprise the barrier number
Figure 817165DEST_PATH_IMAGE004
(N ' be integer), the center position that all barriers are demarcated frame is followed successively by
Figure 2013103827685100002DEST_PATH_IMAGE005
with average gray in frame
Figure 761987DEST_PATH_IMAGE006
, ;
One undetected counter and a detection counter are set, and the initial value of all counters is zero;
Carry out undetected flase drop judgement, comprise the following steps:
1) calculate
Figure 2013103827685100002DEST_PATH_IMAGE009
( ) in the demarcation frame of individual barrier and testing result data
Figure 370320DEST_PATH_IMAGE010
Figure 2013103827685100002DEST_PATH_IMAGE011
the difference of two squares of the central point skew of individual demarcation frame
Figure 603987DEST_PATH_IMAGE012
:
Figure 2013103827685100002DEST_PATH_IMAGE013
;
2) if to (
Figure 986743DEST_PATH_IMAGE014
) have , wherein
Figure 725023DEST_PATH_IMAGE016
be a predetermined threshold value, numerical value is 150 ~ 250, and judgement detects relatively large deviation, exists real obstruction undetected, and undetected counter adds 1; If can find a barrier
Figure 949331DEST_PATH_IMAGE010
meet , judgement is found one and the
Figure 338724DEST_PATH_IMAGE009
the detected barrier of the algorithm that individual barrier is complementary by this obstacle tag is
Figure 436124DEST_PATH_IMAGE018
, in the demarcation frame of its correspondence, gray average is
Figure 2013103827685100002DEST_PATH_IMAGE019
, carry out next step;
3) calculate
Figure 910968DEST_PATH_IMAGE020
frame and
Figure 673388DEST_PATH_IMAGE018
the average gray matching degree difference of two squares of frame
Figure 2013103827685100002DEST_PATH_IMAGE021
:
Figure 668020DEST_PATH_IMAGE022
;
4) if
Figure 2013103827685100002DEST_PATH_IMAGE023
, wherein
Figure 185589DEST_PATH_IMAGE024
for predetermined threshold value, its numerical value is 50 ~ 150, and thinking to detect has relatively large deviation, has the real obstruction flase drop; Otherwise, be considered as correct barrier accurately being detected, detection counter is added to 1; And
After having judged demarcation frames all in the testing result data, output statistics verification and measurement ratio, loss and false drop rate.
The present invention has following technique effect:
I, can add up the part of isolating undetected in the detected barrier of algorithm and flase drop, facilitate the follow-up calculating of carrying out every detection index;
II, for the improvement supervisory system science data are provided, can under test environment, react the detection quality of vehicle detecting system.The verification method of this kind of road vehicle detection system is not only applicable to single-frame images, and is applicable to multiple image.
The accompanying drawing explanation
The process flow diagram of the verification method that Fig. 1 is the road vehicle detection system.
Embodiment
Below each step of the verification method of road vehicle detection system of the present invention is at length resolved and illustrated, for convenience of describing, the verification method in the single frames situation is that example describes.
The vehicle of discussion of the present invention is the target vehicle in range of interest, and in general, distant vehicle does not constitute threat to driving, and this retrains apart from defining with default lane line of distance.Realize vehicle location in the lane line scope, and utilize detection algorithm to survey search.The above zone of lane line vanishing point belongs to the safety zone of detection, and detection system does not go to detect this part safety zone.And the zone partly or entirely entered in lane line is set as hazardous location, need system early warning.
Therefore sensing range is zone and all or part of vehicle that enters lane line below the lane line vanishing point; The calculating of verification and measurement ratio also is equivalent to the verification and measurement ratio of considering the following vehicle of vanishing point.
The verification method of road vehicle detection system of the present invention, in the video image collected, is marked the rectangle frame for vehicle that detects (hereinafter referred to as demarcating frame) by relevant detection algorithm, and records the
Figure 898461DEST_PATH_IMAGE009
the upper left corner coordinate of car
Figure 2013103827685100002DEST_PATH_IMAGE025
with lower right corner coordinate .
The numerical procedure detailed step that the vehicle detection rate is concrete is as follows:
(1) provide a standard exercise video, in this standard exercise video, the number of barrier is that N(N is integer), the central point of the default demarcation frame of each barrier is
Figure 562977DEST_PATH_IMAGE001
, the default average gray of demarcating in frame is respectively
Figure 189131DEST_PATH_IMAGE002
,
Figure 389299DEST_PATH_IMAGE003
.Wherein,
Figure 493521DEST_PATH_IMAGE009
(
Figure 712013DEST_PATH_IMAGE003
) center point coordinate of individual demarcation frame can be expressed as:
Figure 2013103827685100002DEST_PATH_IMAGE027
；
The (
Figure 930953DEST_PATH_IMAGE003
) image pixel dot matrix in the frame of individual demarcation frame is expressed as:
Figure 2013103827685100002DEST_PATH_IMAGE029
，
The pixel average of this frame is expressed as: .
(2) utilize the road vehicle detection system to be detected above-mentioned standard exercise video, specifically detect the vehicle in lane line in the every two field picture of input video, and obtain its testing result data from this system.The testing result data comprise the barrier number
Figure 177444DEST_PATH_IMAGE004
(
Figure 958449DEST_PATH_IMAGE004
for integer), the center position that each barrier is demarcated frame is respectively
Figure 54581DEST_PATH_IMAGE005
,
Figure 500606DEST_PATH_IMAGE007
, and the average gray in each frame is respectively .Wherein,
Figure 2013103827685100002DEST_PATH_IMAGE031
with
Figure 645596DEST_PATH_IMAGE032
computing method and step (1) in
Figure 229024DEST_PATH_IMAGE020
with
Figure 2013103827685100002DEST_PATH_IMAGE033
computing method identical.
(3) set accurate detection counter (abbreviation detection counter) counter1 and a undetected counter counter2, initial value is 0.
(4) carry out undetected flase drop judgement:
1) calculate
Figure 541057DEST_PATH_IMAGE009
(
Figure 526331DEST_PATH_IMAGE003
) individual demarcation frame and road vehicle detection system detected
Figure 649139DEST_PATH_IMAGE010
(
Figure 719863DEST_PATH_IMAGE014
) difference of two squares of central point skew of frame :
Figure 675366DEST_PATH_IMAGE013
Figure 156026DEST_PATH_IMAGE034
.
2) if
Figure 2013103827685100002DEST_PATH_IMAGE035
, (
Figure 261517DEST_PATH_IMAGE016
be a predetermined threshold value, numerical value is 150 ~ 250) think to detect that relatively large deviation is arranged, exist real obstruction undetected, undetected counter adds one, counter2=counter2+1, performs step 5); If
Figure 180931DEST_PATH_IMAGE036
,
Figure 875218DEST_PATH_IMAGE010
demarcate frame and the
Figure 526779DEST_PATH_IMAGE009
individual barrier is complementary, by
Figure 209363DEST_PATH_IMAGE010
the demarcation collimation mark is designated as
Figure 604573DEST_PATH_IMAGE018
, in its corresponding frame, gray average is
Figure 215682DEST_PATH_IMAGE019
, carry out next step.
3) calculate
Figure 303724DEST_PATH_IMAGE020
frame and
Figure 383807DEST_PATH_IMAGE018
the average gray matching degree difference of two squares of frame
Figure 317128DEST_PATH_IMAGE021
:
Figure 2013103827685100002DEST_PATH_IMAGE037
.
4) if
Figure 48323DEST_PATH_IMAGE023
, wherein
Figure 307266DEST_PATH_IMAGE024
for predetermined threshold value, its numerical value is 50 ~ 150, and thinking to detect has relatively large deviation, has the real obstruction flase drop, performs step 5); Otherwise judgement has detected correct barrier, this indicia framing does not have flase drop, and detection counter is added to 1, and counter1=counter1+1, perform step 5).
5) whether judgement is demarcated frame and is all checked completely, if check completely, statistics, calculated, if do not check completely, continues to check the next frame of demarcating.
(5) after the detection, the vehicle detection index is calculated:
The vehicle detection rate:
Figure 609066DEST_PATH_IMAGE038
;
Loss:
Figure 2013103827685100002DEST_PATH_IMAGE039
;
False drop rate:
Figure 611657DEST_PATH_IMAGE040
.
(6) output the result, and exceed corresponding early warning value alarm in loss or false drop rate.
Whether flase drop is undetected can accurately to judge by above step the barrier vehicle detected in a frame, and counts concrete number, in like manner can apply in the statistics of multiple image.
The present invention can add up the part of isolating undetected in the detected barrier of algorithm and flase drop, facilitates the follow-up calculating of carrying out every detection index, for the improvement supervisory system provides science data, can under test environment, react the detection quality of vehicle detecting system.

Claims (1)

1. the verification method of a road vehicle detection system, is characterized in that, comprises the following steps:
One standard exercise video is provided, and in this standard exercise video, the number of barrier is that N(N is integer), the central point of the default demarcation frame of all barriers is followed successively by
Figure 980089DEST_PATH_IMAGE001
, and the default average gray of demarcating in frame is respectively
Figure 228537DEST_PATH_IMAGE002
,
Figure 2013103827685100001DEST_PATH_IMAGE003
;
Utilize described road vehicle detection system to be detected described standard exercise video, and obtain its testing result data from this system, described testing result data comprise the barrier number (N ' be integer), the center position that all barriers are demarcated frame is followed successively by
Figure 2013103827685100001DEST_PATH_IMAGE005
with average gray in frame
Figure 489196DEST_PATH_IMAGE006
,
Figure 517195DEST_PATH_IMAGE007
;
One undetected counter and a detection counter are set, and the initial value of all counters is zero;
Carry out undetected flase drop judgement, comprise the following steps:
1) calculate
Figure 2013103827685100001DEST_PATH_IMAGE009
(
Figure 885728DEST_PATH_IMAGE003
) in the demarcation frame of individual barrier and testing result data
Figure 13084DEST_PATH_IMAGE010
Figure 2013103827685100001DEST_PATH_IMAGE011
the difference of two squares of the central point skew of individual demarcation frame
Figure 539006DEST_PATH_IMAGE012
:
?；
2) if to (
Figure 593735DEST_PATH_IMAGE014
) have
Figure 2013103827685100001DEST_PATH_IMAGE015
, wherein
Figure 891993DEST_PATH_IMAGE016
be a predetermined threshold value, numerical value is 150 ~ 250, and judgement detects relatively large deviation, exists real obstruction undetected, and undetected counter adds 1; If can find a barrier
Figure 279112DEST_PATH_IMAGE010
meet
Figure 2013103827685100001DEST_PATH_IMAGE017
, judgement is found one and the
Figure 337329DEST_PATH_IMAGE009
the detected barrier of the algorithm that individual barrier is complementary by this obstacle tag is
Figure 227924DEST_PATH_IMAGE018
, in the demarcation frame of its correspondence, gray average is
Figure 2013103827685100001DEST_PATH_IMAGE019
, carry out next step;
3) calculate
Figure 2013103827685100001DEST_PATH_IMAGE021
frame and the average gray matching degree difference of two squares of frame
Figure 758449DEST_PATH_IMAGE022
:
Figure 2013103827685100001DEST_PATH_IMAGE023
；
4) if
Figure 869624DEST_PATH_IMAGE024
, wherein
Figure 2013103827685100001DEST_PATH_IMAGE025
for predetermined threshold value, its numerical value is 50 ~ 150, and thinking to detect has relatively large deviation, has the real obstruction flase drop; Otherwise, be considered as correct barrier accurately being detected, detection counter is added to 1; And
After having judged demarcation frames all in the testing result data, output statistics verification and measurement ratio, loss and false drop rate.
CN201310382768.5A 2013-08-28 2013-08-28 A kind of verification method of road vehicle detection system Expired - Fee Related CN103473925B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201310382768.5A CN103473925B (en) 2013-08-28 2013-08-28 A kind of verification method of road vehicle detection system

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201310382768.5A CN103473925B (en) 2013-08-28 2013-08-28 A kind of verification method of road vehicle detection system

Publications (2)

Publication Number Publication Date
CN103473925A true CN103473925A (en) 2013-12-25
CN103473925B CN103473925B (en) 2016-08-10

Family

ID=49798753

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201310382768.5A Expired - Fee Related CN103473925B (en) 2013-08-28 2013-08-28 A kind of verification method of road vehicle detection system

Country Status (1)

Country Link
CN (1) CN103473925B (en)

Cited By (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109544907A (en) * 2018-10-23 2019-03-29 大唐软件技术股份有限公司 A kind of vehicle count method, device
CN110958423A (en) * 2018-09-26 2020-04-03 浙江宇视科技有限公司 Vehicle detection rate determining method and device
CN111626106A (en) * 2020-04-17 2020-09-04 惠州市德赛西威智能交通技术研究院有限公司 Camera vehicle detection rate statistical method and device
CN111861966A (en) * 2019-04-18 2020-10-30 杭州海康威视数字技术股份有限公司 Model training method and device and defect detection method and device
CN113032249A (en) * 2021-03-05 2021-06-25 北京百度网讯科技有限公司 Test method, device and equipment of traffic flow monitoring system

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JPH11306483A (en) * 1998-04-16 1999-11-05 Toshiba Corp Detection system, vehicle detection system and detection method
WO2006073647A2 (en) * 2004-12-03 2006-07-13 Sarnoff Corporation Method and apparatus for unsupervised learning of discriminative edge measures for vehicle matching between non-overlapping cameras
CN101615342A (en) * 2008-06-27 2009-12-30 青岛海信电子产业控股股份有限公司 A kind of vehicle checking method
JP2010176302A (en) * 2009-01-28 2010-08-12 Mitsubishi Electric Corp Vehicle detection device, vehicle detection system, vehicle detection method for vehicle detection device, and vehicle detection program
CN102779272A (en) * 2012-06-29 2012-11-14 惠州市德赛西威汽车电子有限公司 Switching method for vehicle detection modes
CN102915453A (en) * 2012-08-30 2013-02-06 华南理工大学 Real-time feedback and update vehicle detection method

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JPH11306483A (en) * 1998-04-16 1999-11-05 Toshiba Corp Detection system, vehicle detection system and detection method
WO2006073647A2 (en) * 2004-12-03 2006-07-13 Sarnoff Corporation Method and apparatus for unsupervised learning of discriminative edge measures for vehicle matching between non-overlapping cameras
CN101615342A (en) * 2008-06-27 2009-12-30 青岛海信电子产业控股股份有限公司 A kind of vehicle checking method
JP2010176302A (en) * 2009-01-28 2010-08-12 Mitsubishi Electric Corp Vehicle detection device, vehicle detection system, vehicle detection method for vehicle detection device, and vehicle detection program
CN102779272A (en) * 2012-06-29 2012-11-14 惠州市德赛西威汽车电子有限公司 Switching method for vehicle detection modes
CN102915453A (en) * 2012-08-30 2013-02-06 华南理工大学 Real-time feedback and update vehicle detection method

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
吕慧娟等: "基于Adaboost cascade的车牌检测技术", 《河南大学学报(自然科学版)》, vol. 38, no. 03, 31 May 2008 (2008-05-31), pages 313 - 315 *

Cited By (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110958423A (en) * 2018-09-26 2020-04-03 浙江宇视科技有限公司 Vehicle detection rate determining method and device
CN110958423B (en) * 2018-09-26 2021-08-31 浙江宇视科技有限公司 Vehicle detection rate determining method and device
CN109544907A (en) * 2018-10-23 2019-03-29 大唐软件技术股份有限公司 A kind of vehicle count method, device
CN111861966A (en) * 2019-04-18 2020-10-30 杭州海康威视数字技术股份有限公司 Model training method and device and defect detection method and device
CN111861966B (en) * 2019-04-18 2023-10-27 杭州海康威视数字技术股份有限公司 Model training method and device and defect detection method and device
CN111626106A (en) * 2020-04-17 2020-09-04 惠州市德赛西威智能交通技术研究院有限公司 Camera vehicle detection rate statistical method and device
CN113032249A (en) * 2021-03-05 2021-06-25 北京百度网讯科技有限公司 Test method, device and equipment of traffic flow monitoring system

Also Published As

Publication number Publication date
CN103473925B (en) 2016-08-10

Similar Documents

Publication Publication Date Title
US10885777B2 (en) Multiple exposure event determination
US10032085B2 (en) Method and system to identify traffic lights by an autonomous vehicle
KR100969995B1 (en) System of traffic conflict decision for signalized intersections using image processing technique
CN103456172B (en) A kind of traffic parameter measuring method based on video
CN112700470B (en) Target detection and track extraction method based on traffic video stream
TWI452540B (en) Image based detecting system and method for traffic parameters and computer program product thereof
CN107025432B (en) A kind of efficient lane detection tracking and system
CN109922439A (en) The fusion method of multi-sensor data, the object detection method based on V2X and system
CN103226891B (en) Video-based vehicle collision accident detection method and system
CN103473925A (en) Verification method of road vehicle detection system
CN109064495A (en) A kind of bridge floor vehicle space time information acquisition methods based on Faster R-CNN and video technique
CN105844222A (en) System and method for front vehicle collision early warning based on visual sense
KR20140112171A (en) Display system of vehicle information based on the position
CN103021182B (en) Method and device for monitoring motor vehicle in case of regulation violation for running red light
CN111079589B (en) Automatic height detection method based on depth camera shooting and height threshold value pixel calibration
KR101834838B1 (en) System and method for providing traffic information using image processing
Wang et al. Advanced driver‐assistance system (ADAS) for intelligent transportation based on the recognition of traffic cones
CN109101939A (en) Determination method, system, terminal and the readable storage medium storing program for executing of state of motion of vehicle
CN103528531A (en) Intelligent Internet of Things image detection system for small vehicle parameters
CN106600987A (en) Intersection traffic signal control method and system having multi-dimensional detection function
CN107067778A (en) A kind of vehicle antitracking method for early warning and device
CN106485697A (en) A kind of roadbed subsidence based on binocular vision and foreign matter detecting method
CN113071500A (en) Method and device for acquiring lane line, computer equipment and storage medium
CN112185103A (en) Traffic monitoring method and device and electronic equipment
CN104408942A (en) Intelligent vehicle speed measuring device and method

Legal Events

Date Code Title Description
C06 Publication
PB01 Publication
C10 Entry into substantive examination
SE01 Entry into force of request for substantive examination
C14 Grant of patent or utility model
GR01 Patent grant
CB03 Change of inventor or designer information

Inventor after: Zhou Zhiheng

Inventor after: Huang Weilie

Inventor after: Du Sunzheng

Inventor after: Zhang Wenting

Inventor after: Chen Miaowei

Inventor after: Ou Xiaowen

Inventor after: Zhong Chen

Inventor before: Zhou Zhiheng

Inventor before: Huang Weilie

Inventor before: Du Sunzheng

Inventor before: Zhang Wenting

Inventor before: Chen Miaowei

Inventor before: Ou Xiaowen

COR Change of bibliographic data
CF01 Termination of patent right due to non-payment of annual fee

Granted publication date: 20160810

Termination date: 20180828

CF01 Termination of patent right due to non-payment of annual fee