CN105354610A - Random Hough transform-based people counting method - Google Patents
Random Hough transform-based people counting method Download PDFInfo
- Publication number
- CN105354610A CN105354610A CN201410411719.4A CN201410411719A CN105354610A CN 105354610 A CN105354610 A CN 105354610A CN 201410411719 A CN201410411719 A CN 201410411719A CN 105354610 A CN105354610 A CN 105354610A
- Authority
- CN
- China
- Prior art keywords
- image
- people
- circle
- difference
- algorithm
- 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
Landscapes
- Image Analysis (AREA)
Abstract
The invention belongs to the technical field of computer video image processing, and provides a random Hough transform-based people counting method. The random Hough transform-based people counting method includes the following steps: acquiring a video stream image in a monitoring area, serving the video stream image as an input image, obtaining a difference image through an inter-frame difference method, and performing binarization processing on the difference image to obtain a motion target area; performing edge detecting on the motion target area through a Sobel operator to obtain a motion target profile; only accumulating parameter allocation units obtained from may-to-one mapping by adoption of a dynamic linked list structure, randomly sampling three or more than three points which are not in the same straight line to determine a circle, and extracting people head areas; and tracking and counting the extracted people head areas by adoption of an EKM algorithm. According to the invention, extensive calculation of one-to-many mapping can be avoided by adoption of the random Hough transform, less internal storage can be occupied through the dynamic linked list structure, and the efficiency and the accuracy of people counting for pedestrians in the monitoring area can be improved.
Description
Technical field
The present invention relates to a kind of Video Image processing technology field, particularly a kind of demographic method based on random Hough transformation.
Background technology
Hough transform is a kind of parameter estimation techniques using voting principle, and its principle is the point-line duality utilizing image space and Hough parameter space, and the test problems in image space is transformed into parameter space.By carrying out simple cumulative statistics in parameter space, then find the method detection of straight lines of totalizer peak value at Hough parameter space.The essence of Hough transform is that the pixel in image space with certain relation is carried out cluster, finds the parameter space accumulation corresponding point that these pixels can be connected by a certain analytical form.When parameter space is no more than two dimension, this conversion has desirable effect.
Hough transform thought is: the straight line in point under coordinates of original image coordinates system is corresponding parameter coordinate system, a point under original coordinate system that the straight line of same parameter coordinate system is corresponding, then, the institute of straight line is presented a little under original coordinate system, their slope and intercept are identical, so they correspond to same point under parameter coordinate system.Like this by after under each spot projection under original coordinate system to parameter coordinate system, under seeing parameter coordinate system, whether there is convergence point, the straight line under original coordinate system that such convergence point is just corresponding.
Based on the characteristic of Hough transform, it is in the various fields such as widespread use Video Image process.But, because image to be detected is generally all subject to the interference of outside noise, signal to noise ratio (S/N ratio) is lower, thus causes the actual effect of Hough transform of the prior art in Video Image process not good, when causing adding up the motion pedestrian in guarded region, flase drop or undetected occurs.
In view of this, be necessary to be improved carrying out demographics based on Hough transform in prior art, to solve the problem.
Summary of the invention
The object of the present invention is to provide a kind of demographic method based on random Hough transformation, in order to improve, statistical accuracy is carried out to the pedestrian's number in guarded region, reduce false drop rate and loss.
For achieving the above object, the invention discloses a kind of demographic method based on random Hough transformation, comprising:
The video streaming image of S1, acquisition guarded region is as input picture;
S2, according to input picture, obtain difference image by frame differential method process, and binary conversion treatment is carried out to difference image, obtain motion target area;
S3, by Sobel operator, rim detection is carried out to motion target area, obtain moving target profile;
S4, dynamic link table structure is adopted only to map to one the parametric distribution unit obtained add up many, and the point of stochastic sampling more than three or three not on same straight line is to determine a circle, thus loop truss is carried out to described moving target profile, extract people's head region;
S5, EKM algorithm is utilized to follow the tracks of the people's head region extracted and count.
As a further improvement on the present invention, described step S1 is specially: obtain the video streaming image of guarded region as input picture by video camera, described guarded region is positioned at immediately below video camera.
As a further improvement on the present invention, " frame differential method process " in described step S2 is specially: the input picture obtained according to step S1, utilizes current frame image and previous frame image to do inter-frame difference computing and obtain difference image,
The computing formula of described inter-frame difference computing is: D
k(x, y)=F
k(x, y)-F
k-1(x, y);
Wherein, F
k-1(x, y) is the gray-scale value of pixel in previous frame image,
for the gray-scale value of pixel in current frame image, D
kthe difference image that (x, y) is previous frame image and current frame image.
As a further improvement on the present invention, described step S3 is specially: use the Sobel operator of 3*3 to carry out rim detection to the motion target area that described step S2 obtains, obtain moving target profile.
As a further improvement on the present invention, the algorithm that " EKM algorithm " in described step S5 adopts Kalman filter to combine with Meanshift algorithm.
Compared with prior art, the invention has the beneficial effects as follows: pass through random Hough transformation, avoid the huge calculated amount that one-to-many maps, and reduce taking internal memory by dynamic link table structure, improve efficiency and the accuracy rate of the pedestrian in guarded region being carried out to demographics.
Accompanying drawing explanation
Fig. 1 is the process flow diagram of a kind of demographic method based on random Hough transformation of the present invention;
Fig. 2 is the principle of work schematic diagram of the video streaming image realizing guarded region in step S2;
Fig. 3 a is the schematic diagram that Sobel operator calculates the Grad in x direction;
Fig. 3 b is the schematic diagram that Sobel operator calculates the Grad in y direction;
Fig. 4 is the schematic diagram that illustrated input picture does Convolution sums computing.
Embodiment
Below in conjunction with each embodiment shown in the drawings, the present invention is described in detail; but should be noted that; these embodiments are not limitation of the present invention; those of ordinary skill in the art are according to these embodiment institute work energy, method or structural equivalent transformations or substitute, and all belong within protection scope of the present invention.
Shown in ginseng Fig. 1, Fig. 1 is the schematic flow sheet of a kind of demographic method embodiment based on random Hough transformation of the present invention.
In the present embodiment, a kind of demographic method based on random Hough transformation, the method comprises the following steps:
First perform step S1, obtain the video streaming image of guarded region as input picture.
Shown in ginseng Fig. 2, a kind of demographic method based on random Hough transformation of the present invention is vertically taken based on video camera and is applicable to outdoor situations and indoor situations.In the present embodiment, this step S1 is specially: obtain the video streaming image of guarded region 30 as input picture by video camera 10, and described guarded region 30 is positioned at immediately below video camera 10.
Concrete, video camera 10 is arranged on directly near gateway 20, and pedestrian can walk up and down on the direction of arrow 201 in gateway 20.The guarded region 30 that video camera 10 obtains can cover the Zone Full of gateway 20 completely.
In the present embodiment, this guarded region 30 is rectangle, can certainly be square or circular or other shapes.Video camera 10 is positioned at directly over the central point 301 of guarded region 30, and we can derive thus, and this guarded region 30 is positioned at immediately below video camera 10.
Then perform step S2, according to input picture, obtain difference image by frame differential method process, and binary conversion treatment is carried out to difference image, obtain motion target area.
In the present embodiment, described frame differential method process is specially: the input picture obtained according to step S1, utilizes current frame image and previous frame image to do inter-frame difference computing and obtain difference image.
The computing formula of this inter-frame difference computing is: D
k(x, y)=F
k(x, y)-F
k-1(x, y);
Wherein, F
k-1(x, y) is the gray-scale value of pixel in previous frame image, F
k(x, y) is the gray-scale value of pixel in current frame image, D
kthe difference image that (x, y) is previous frame image and current frame image.
Then carry out binary conversion treatment to difference image, the operational formula of binary conversion treatment is as follows:
Wherein, R
k(x, y) bianry image for obtaining after carrying out method of difference process, Q is partition threshold.Concrete, in the present embodiment, this partition threshold Q is set as 40.
Work as R
kwhen (x, y) is 0, this pixel is background dot;
Work as R
kwhen (x, y) is 1, this pixel is foreground point (i.e. moving object).
Then perform step S3, by Sobel operator, rim detection carried out to motion target area, obtain moving target profile.
Edge refers to the most significant part of image local brightness change, mainly be present in target and target, object and background, between region and region, rim detection is the most fundamental operation of detected image local marked change, and the discrete approximation function of the marked change available gradient value of image intensity value detects.
Shown in composition graphs 3a, Fig. 3 b and Fig. 4, be set to f (x, y) to the input picture of a frame binaryzation at the pixel value of certain pixel, the Grad computing formula for this pixel is as follows:
Wherein, the Grad that M (x, y) asks for pixel (x, y) place, S
x, S
ypixel (x, y) is calculated respectively along the Grad on x, y direction for utilizing sobel operator.
Wherein Fig. 3 a is the schematic diagram that Sobel operator calculates this pixel (x, y) Grad in the x-direction; Fig. 3 b is the schematic diagram that Sobel operator calculates this pixel (x, y) Grad in the y-direction.
S
x, S
yrepresent that sobel operator does convolution algorithm, the Z in Fig. 4 with the gray level of Image neighborhood as shown in Figure 4 respectively
i(i=1,2 ..., 9) represent the gray-scale value of the pixel around this pixel (x, y) eight neighborhood, Grad S
xand S
yas follows with formulae discovery:
That is, image is respectively along the Grad on x, y direction at pixel (x, y) place:
S
x＝(Z
1+2Z
2+Z
3)-(Z
7+2Z
8+Z
9)；
S
y＝(Z
1+2Z
4+Z
7)-(Z
3+2Z
6+Z
9)。
Sobel operator is one of operator in image procossing, and be mainly used as rim detection, it is a kind of discreteness difference operator, is used for the gradient approximation of arithmograph image brightness function.In the present embodiment, this Sobel operator comprises the matrix of two group 3 × 3, be respectively for asking pixel along the Grad on x, y direction, it and each pixel neighborhood of a point gray level in input picture are as shown in Figure 4 done Convolution sums computing, then suitable threshold values K is chosen, to extract edge image.
Concrete, the computing formula of this Convolution sums computing is as follows,
Wherein, threshold k is 200.
When f (x, y) is 1, namely this pixel is judged to be the marginal point of input picture.
Following execution step S4, dynamic link table structure is adopted only to map to one the parametric distribution unit obtained add up many, and the point of stochastic sampling more than three or three not on same straight line is to determine a circle, thus loop truss is carried out to described moving target profile, extract people's head region.
From depression angle, the contouring head of guarded region 30 one skilled in the art is similar to circle, and contouring head pixel must be present in same class rounded edge.For this feature, in the present embodiment, by random Hough transformation, loop truss is carried out to moving target profile, to determine people's head region of pedestrian.
Random Hough transformation (RHT) adopt many to one mapping, avoid traditional Hough transform one to the huge calculated amount mapped more; And adopt dynamic link table structure, only map to one the parametric distribution unit obtained accumulate many, thus reduce memory requirements, make RHT have parameter space infinity, any advantages of higher of parameters precision simultaneously.During based on RHT process complicated image, because stochastic sampling can cause a large amount of invalid samplings and accumulation, algorithm performance is declined.For this reason, present embodiment proposes the point of stochastic sampling 3 not on same straight line, carries out loop truss.
If D is the border point set of moving target profile, P is the parameters unit collection in Circle Parameters space, and wherein P is a dynamic link table, to record the information of the circle found.Can determine a circle (mathematical theorem) according to the point of 3 not on same straight line, the point of random selecting 3 not on same straight line from D, calculates parameter p and the radius r of these three determined circles of point.
If r < is r
th, then search for Circle Parameters unit collection P, whether there is a parameter p
c, make p
cwith the error of p within permissible range, if p
cexist, then by Parameter units p
ccalculated value score add 1 and by parameters unit p
cupgrade; If no, then insert new parameters unit p in Circle Parameters unit collection P.As parameters unit p
ccount value score when reaching threshold value N, circle corresponding to this parameter is candidate's circle, calculates the moving target profile pixel number dropped on this candidate's circle be greater than set minimal point M by accumulation
min, then confirm that this candidate circle is for true circle, deletes the pixel on this circle, and discharges the internal memory that in Circle Parameters unit collection P, all parameters unit take, then carry out the detection of next circle from D.
If do not know the number of the number of people in guarded region in advance, can to specify in the round process of detection one allow the maximum cycle K of stochastic sampling
max, and when still not having the score of parameters unit to reach threshold value N in Circle Parameters unit collection P, then think that Hough transform can not detect more circle, loop truss terminates.The concrete steps of algorithm are as follows:
S41: tectonic movement objective contour point set D, initiated circle parameters unit collection P=Null, cycle index k=0.
S42: the some d of random selecting 3 not on same straight line from D
1, d
2, d
3.
S43: solve round characteristic parameter p and radius r by these 3 points.If r < is r
th, then redirect performs step S44; Otherwise redirect performs step S47.Here r
th=15.
S44: look for round characteristic parameter p in circle characteristic parameter unit collection P
c, satisfy condition || p-p
c||≤δ, if find round characteristic parameter p
c, then redirect performs step S46; Otherwise redirect performs step S45.Here δ=1.
S45: be inserted into by circle characteristic parameter p in Circle Parameters unit collection P, its corresponding count value score is 1, redirect performs step S47.
S46: characteristic parameter p will be justified
ccount value score add 1, and by p
cupgrade.
If count value score is less than specify threshold value N, redirect performs step S47; If count value score is greater than or equal to specify threshold value N, then redirect performs step S48.Here N=3.
S47:k=k+1, if k > is K
max, loop truss terminates; Otherwise redirect performs step S42.
S48:p
cfor candidate's circle characteristic parameter, if the marginal point m > M of this parameter corresponding circle
minif redirect performs step S49, otherwise false Circle Parameters is removed p from Circle Parameters unit collection P
c, redirect performs step S42.Here M
min=20.
S49:p
cfor true Circle Parameters, allowing the point on character pair to remove from D by dropping on parameter, judging whether the number of the circle detected has reached defined amount or whether the cycle index for detecting a circle reaches maximum times.If so, then terminate; Otherwise reset P=Null, k=0, redirect performs step S42.
K
maxby regulation the round process of detection one in permission sample maximum cycle; M
minit is the necessary minimal point of circle; P is the parameters unit collection in Circle Parameters space, is a dynamic link table; M falls counting on candidate's circle in image space.
Finally perform step S5, utilize EKM algorithm to follow the tracks of the people's head region extracted and count.
" EMK algorithm " is specially: the method adopting Kalman filter to combine with Meanshift algorithm is followed the tracks of moving target.Center point coordinate Z (k) of the people's head region obtained is detected according to former frame, Kalman filter is utilized to predict center point coordinate Z ' (k) position in the current frame of people's head region, using the starting point of the target's center that prediction coordinate points Z ' (k) calculated is followed the tracks of as Meanshift, then utilize Meanshift algorithm in the neighborhood of this starting point Z ' (k), find the optimum coordinates of the central point of people's head region of tracking.After obtaining the optimum coordinates of the central point of people's head region of following the tracks of, using this optimum coordinates as the observed reading of next frame Kalman filter to carry out the follow-up prediction of number of people regional center point to following the tracks of.
The center point coordinate of the people's head region predicted due to Kalman filter compares the center point coordinate of center point coordinate closer to people's head region of present frame that previous frame detects the people's head region obtained, so carry out iterative tracking target when present frame coordinate at utilization Meanshift to it, effectively can reduce the number of times of iterative computation, shorten the recognition time of integral monitoring target.
A series of detailed description listed is above only illustrating for feasibility embodiment of the present invention; they are also not used to limit the scope of the invention, all do not depart from the skill of the present invention equivalent implementations done of spirit or change all should be included within protection scope of the present invention.
Claims (5)
1. based on a demographic method for random Hough transformation, it is characterized in that, comprising:
The video streaming image of S1, acquisition guarded region is as input picture;
S2, according to input picture, obtain difference image by frame differential method process, and binary conversion treatment is carried out to difference image, obtain motion target area;
S3, by Sobel operator, rim detection is carried out to motion target area, obtain moving target profile;
S4, dynamic link table structure is adopted only to map to one the parametric distribution unit obtained add up many, and the point of stochastic sampling more than three or three not on same straight line is to determine a circle, thus loop truss is carried out to described moving target profile, extract people's head region;
S5, EKM algorithm is utilized to follow the tracks of the people's head region extracted and count.
2. demographic method according to claim 1, is characterized in that, described step S1 is specially: obtain the video streaming image of guarded region as input picture by video camera, described guarded region is positioned at immediately below video camera.
3. demographic method according to claim 1, it is characterized in that, " frame differential method process " in described step S2 is specially: the input picture obtained according to step S1, utilizes current frame image and previous frame image to do inter-frame difference computing and obtain difference image
The computing formula of described inter-frame difference computing is: D
k(x, y)=F
k(x, y)-F
k-1(x, y);
Wherein, F
k-1(x, y) is the gray-scale value of pixel in previous frame image, F
k(x, y) is the gray-scale value of pixel in current frame image, D
kthe difference image that (x, y) is previous frame image and current frame image.
4. demographic method according to claim 1, is characterized in that, described step S3 is specially: use the Sobel operator of 3*3 to carry out rim detection to the motion target area that described step S2 obtains, obtain moving target profile.
5. demographic method according to claim 1, is characterized in that, the algorithm that " EKM algorithm " in described step S5 adopts Kalman filter to combine with Meanshift algorithm.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410411719.4A CN105354610A (en) | 2014-08-18 | 2014-08-18 | Random Hough transform-based people counting method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410411719.4A CN105354610A (en) | 2014-08-18 | 2014-08-18 | Random Hough transform-based people counting method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN105354610A true CN105354610A (en) | 2016-02-24 |
Family
ID=55330577
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201410411719.4A Pending CN105354610A (en) | 2014-08-18 | 2014-08-18 | Random Hough transform-based people counting method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN105354610A (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106327519A (en) * | 2016-08-19 | 2017-01-11 | 杭州智诺科技股份有限公司 | Human head detection method based on Hough conversion |
| CN106652343A (en) * | 2016-12-16 | 2017-05-10 | 合肥寰景信息技术有限公司 | Human body falling identification and early warning system based on video monitoring |
| CN106846354A (en) * | 2017-01-23 | 2017-06-13 | 中国人民解放军海军航空工程学院 | A kind of Book Inventory method on frame converted based on image segmentation and random hough |
| CN117132948A (en) * | 2023-10-27 | 2023-11-28 | 南昌理工学院 | Scenic spot tourist flow monitoring method, system, readable storage medium and computer |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20100021009A1 (en) * | 2007-01-25 | 2010-01-28 | Wei Yao | Method for moving targets tracking and number counting |
| CN102831472A (en) * | 2012-08-03 | 2012-12-19 | 无锡慧眼电子科技有限公司 | People counting method based on video flowing image processing |
| CN102867349A (en) * | 2012-08-20 | 2013-01-09 | 无锡慧眼电子科技有限公司 | People counting method based on elliptical ring template matching |
| CN102867177A (en) * | 2012-09-19 | 2013-01-09 | 无锡慧眼电子科技有限公司 | People number counting method based on image grey level matching |
| CN103049787A (en) * | 2011-10-11 | 2013-04-17 | 汉王科技股份有限公司 | People counting method and system based on head and shoulder features |
-
2014
- 2014-08-18 CN CN201410411719.4A patent/CN105354610A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20100021009A1 (en) * | 2007-01-25 | 2010-01-28 | Wei Yao | Method for moving targets tracking and number counting |
| CN103049787A (en) * | 2011-10-11 | 2013-04-17 | 汉王科技股份有限公司 | People counting method and system based on head and shoulder features |
| CN102831472A (en) * | 2012-08-03 | 2012-12-19 | 无锡慧眼电子科技有限公司 | People counting method based on video flowing image processing |
| CN102867349A (en) * | 2012-08-20 | 2013-01-09 | 无锡慧眼电子科技有限公司 | People counting method based on elliptical ring template matching |
| CN102867177A (en) * | 2012-09-19 | 2013-01-09 | 无锡慧眼电子科技有限公司 | People number counting method based on image grey level matching |
Non-Patent Citations (3)
| Title |
|---|
| 徐培智等: "基于随机Hough变换的人头检测", 《计算机工程》 * |
| 袁胜智等: "一种基于Kalman_mean shift的自适应跟踪算法", 《激光与红外》 * |
| 韩涛等: "Kalman滤波融合优化Mean Shift的目标跟踪算法", 《光电工程》 * |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106327519A (en) * | 2016-08-19 | 2017-01-11 | 杭州智诺科技股份有限公司 | Human head detection method based on Hough conversion |
| CN106327519B (en) * | 2016-08-19 | 2019-11-19 | 杭州智诺科技股份有限公司 | Number of people detection method based on Hough transform |
| CN106652343A (en) * | 2016-12-16 | 2017-05-10 | 合肥寰景信息技术有限公司 | Human body falling identification and early warning system based on video monitoring |
| CN106846354A (en) * | 2017-01-23 | 2017-06-13 | 中国人民解放军海军航空工程学院 | A kind of Book Inventory method on frame converted based on image segmentation and random hough |
| CN106846354B (en) * | 2017-01-23 | 2019-07-23 | 中国人民解放军海军航空大学 | A kind of Book Inventory method on the frame converted based on image segmentation and random hough |
| CN117132948A (en) * | 2023-10-27 | 2023-11-28 | 南昌理工学院 | Scenic spot tourist flow monitoring method, system, readable storage medium and computer |
| CN117132948B (en) * | 2023-10-27 | 2024-01-30 | 南昌理工学院 | Scenic spot tourist flow monitoring method, system, readable storage medium and computer |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN104217427B (en) | Lane line localization method in a kind of Traffic Surveillance Video | |
| CN103226834B (en) | A kind of image motion target signature point method for fast searching | |
| CN102867349B (en) | People counting method based on elliptical ring template matching | |
| CN109859226B (en) | Detection method of checkerboard corner sub-pixels for graph segmentation | |
| CN102867177B (en) | A kind of demographic method based on gradation of image coupling | |
| CN104978567B (en) | Vehicle checking method based on scene classification | |
| CN102999886B (en) | Image Edge Detector and scale grating grid precision detection system | |
| CN103246896B (en) | A kind of real-time detection and tracking method of robustness vehicle | |
| RU2009102124A (en) | VIDEO INFORMATION PROCESSING DEVICE FOR ALARM SYSTEM | |
| CN110533955B (en) | Method for determining parking space, terminal equipment and computer readable storage medium | |
| US20130243343A1 (en) | Method and device for people group detection | |
| CN108986152B (en) | Foreign matter detection method and device based on difference image | |
| CN105469084A (en) | Rapid extraction method and system for target central point | |
| CN105631418A (en) | People counting method and device | |
| WO2018076392A1 (en) | Pedestrian statistical method and apparatus based on recognition of parietal region of human body | |
| JP2015036980A (en) | Hybrid method and system of video and vision based access control for parking stall occupancy determination | |
| CN103824070A (en) | Rapid pedestrian detection method based on computer vision | |
| CN102855466B (en) | A kind of demographic method based on Computer Vision | |
| CN103413303A (en) | Infrared target segmentation method based on joint obviousness | |
| CN105303153A (en) | Vehicle license plate identification method and apparatus | |
| CN104966304A (en) | Kalman filtering and nonparametric background model-based multi-target detection tracking method | |
| CN104537342B (en) | A kind of express lane line detecting method of combination ridge border detection and Hough transformation | |
| CN105354610A (en) | Random Hough transform-based people counting method | |
| Wang et al. | Pavement crack segmentation algorithm based on local optimal threshold of cracks density distribution | |
| Xiang et al. | Lightweight fully convolutional network for license plate detection |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| CB02 | Change of applicant information |
Address after: 214000 Jiangsu, Huishan Economic Development Zone, wisdom road, No. 1, Tsinghua innovation building, A1501-A1509, Applicant after: ABD SMART EYE ELECTRONICS CO., LTD. Address before: 214000, Jiangsu, Huishan Economic Development Zone, Wuxi, 1, wisdom road, Jiangsu Digital Information Industry Park, Tsinghua innovation building, block A, 15F Applicant before: Wuxi Eye Technology Co., Ltd. |
|
| COR | Change of bibliographic data | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20160224 |
|
| RJ01 | Rejection of invention patent application after publication |