CN105469084A - Rapid extraction method and system for target central point - Google Patents
Rapid extraction method and system for target central point Download PDFInfo
- Publication number
- CN105469084A CN105469084A CN201510810062.3A CN201510810062A CN105469084A CN 105469084 A CN105469084 A CN 105469084A CN 201510810062 A CN201510810062 A CN 201510810062A CN 105469084 A CN105469084 A CN 105469084A
- Authority
- CN
- China
- Prior art keywords
- target
- connected domain
- central point
- max
- rectangular region
- 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
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/22—Image preprocessing by selection of a specific region containing or referencing a pattern; Locating or processing of specific regions to guide the detection or recognition
- G06V10/23—Image preprocessing by selection of a specific region containing or referencing a pattern; Locating or processing of specific regions to guide the detection or recognition based on positionally close patterns or neighbourhood relationships
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Image Analysis (AREA)
Abstract
The invention provides a rapid extraction method and system for a target central point. All connecting areas in an obtained binary image are marked; a target connecting area is detected according to the marked connecting areas; an external rectangular area is determined based on the target connecting area; and thus a target central point coordinate in the external rectangular area is obtained. In the prior art, the multiplication and division operation load for the employed edge detection, Hessian matrix, Hough conversion, and fitting algorithms is heavy. However, according to the provided method, the most operation of the image binaryzation, connecting area marking and center of mass method belongs to the logic operation and adding and subtraction operation, so that the execution efficiency is high.
Description
Technical field
The present invention relates to technical field of image processing, particularly a kind of target central point rapid extracting method and system.
Background technology
The unique point of target refers to the point being convenient to utilize the method for image procossing to obtain coordinate.Unique point has the motion feature identical with target, and therefore, when carrying out target following location, target feature point extraction is committed step.Target takes on a different character because of the difference of geometric configuration a little, and the unique point as circle is the center of circle, the unique point of wire and strip is central point, tessellated unique point is angle point etc.For the target of optical alignment often using central point as unique point, therefore, central point extracts is a kind of modal Feature Points Extraction.
Target central point extraction algorithm has multiple, is mainly divided into following three classes:
The first kind: based on the center extraction algorithm of rim detection and matching.The flow process of such algorithm is: first, by rim detection (be actually and solve first order derivative), obtains the binary image comprising target border; Then, non-target border is removed by morphological method; Finally, utilize fitting algorithm to carry out matching to the borderline coordinate sequence of target, obtain center point coordinate.
If the people such as Yin Yongkai are in the paper delivered " sub-pixel positioning of circular index point and application thereof ", circular index point is target.First, Canny edge detection algorithm is utilized to obtain binaryzation edge image; Secondly, several criterion distinguishing mark point edge (be actually and remove non-circular monumented point edge) is utilized; Secondly, sub-pix process is carried out to the edge obtained, obtain the accurate coordinates at edge; Finally, ellipse fitting method is utilized to obtain the centre coordinate of circular index point.
But the essence of rim detection asks first order derivative, there is the region of grey scale change all can detect border.Utilize several criterions gone out through experimental summary, the background in binary image can be rejected.But when background changes, these criterions can become unreliable, often detect pseudo-edge or true edge disallowable fall.
Equations of The Second Kind: based on the center extraction algorithm of Hessian matrix and Taylor expansion.The flow process of such algorithm is: the Hessian matrix (be actually and solve second derivative) first solving image; Then, solve the eigenwert of Hessian matrix, to determine the location of pixels of target central point; Finally, in central area, distributed function is carried out the second Taylor series, solve extreme value and obtain exact position.
If application number is 200810222666.6, in the scheme of the invention that name is called " a kind of circular facula sub-pel center extracting method and device ", circular light spot is target.First, the initial position at centroid method determination circular light spot center is utilized; Then, then in a window centered by this initial position, according to the location of pixels at the eigenwert determination circular light spot center of Hessian matrix; Finally, in the location of pixels field utilizing the second Taylor series formula determination circular light spot center, the gradation of image function of continuous distribution, solves the sub-pixel location that this gradation of image Function Extreme Value point position is circular light spot center.
But, when Hessian matrix size larger and unusual time, solving eigenwert can be very difficult, even cannot obtain eigenwert.
3rd class: based on the center extraction algorithm of Hough transform.In image procossing, Hough transform is often used to the detection of straight line and circle.When carrying out utilizing Hough transform justifying center extraction, needing to provide radius of a circle scope, can directly provide round centre coordinate after conversion.Hough transform process is actually an integral process.
If the people such as Jiao Shengxi are in the paper delivered " applied research of Hough transformation algorithm in center of circle vision location ", propose a kind of Hough transform Fast Circle detection algorithm of improvement, by analyzing the position relationship of other points in circumferential point and field, judge concavity and the direction, the center of circle of circumferential edges; And the center of circle of circumference is determined with the accumulation result of center of arc's line.
But Hough transform obtains a set meeting this given shape as Hough transformation result by the local maximum calculating accumulated result (i.e. integration) in a parameter space.If can not provide the true scope of key parameter (as radius), conversion process can be very consuming time, and easily detect a large amount of pseudo-target (as circle).
Summary of the invention
The object of the invention is to: a kind of execution efficiency (or speed), reliability are provided, and the target central point rapid extracting method that precision is all higher.
In order to realize the object of foregoing invention, the present invention adopts following technical proposals:
A kind of target central point rapid extracting method, comprises the steps:
Obtain binary image;
Connected domains all in described binary image are marked;
Described connected domain according to mark detects target connected domain;
According to described target connected domain determination circumscribed rectangular region;
Obtain target center point coordinate in described circumscribed rectangular region.
One as target central point rapid extracting method of the present invention is improved, and wherein, marks, comprising connected domains all in described binary image:
4 connected component labeling methods and/or 8 connected component labeling methods are adopted to mark described binary image.
One as target central point rapid extracting method of the present invention is improved, and described 4 connected component labeling methods are to the upper and lower, left and right of current pixel totally 4 the coconnected pixels imparting in direction particular values; Described 8 connected component labeling methods to the upper and lower, left and right of current pixel, upper left, lower-left, upper right, bottom right totally 8 coconnected pixels in direction give particular values.
One as target central point rapid extracting method of the present invention is improved, and wherein, the described connected domain according to mark detects target connected domain, is specially:
According to detection criteria determination target connected domain, described detection criteria provides according to the feature of target, and the feature of described target comprises geometric configuration, physical dimension, gray distribution features.
Described geometric configuration comprises target disc, and geometric configuration criterion is that the line number of pixel in connected domain and columns are close to 1:1; Described physical dimension criterion is that the line number of pixel in connected domain and columns are all greater than 2, and described intensity profile criterion is the gray scale corresponding to connected domain is Gaussian distribution.
One as target central point rapid extracting method of the present invention is improved, and wherein, according to described target connected domain determination circumscribed rectangular region, is specially:
Determine the described horizontal ordinate of target connected domain, the extreme value of ordinate according to following formula, be designated as respectively: x
min, x
max, y
min, y
max, wherein (x
i, y
i) be coordinate points in described target connected domain, N is counting in connected domain
(x
min, y
min), (x
min, y
max), (x
max, y
max), (x
max, y
min) 4 be connected to form described circumscribed rectangular region.
One as target central point rapid extracting method of the present invention is improved, and wherein, obtains target center point coordinate in described circumscribed rectangular region, is specially:
Adopt following formula, utilize gray scale centroid method to obtain target center point coordinate in described circumscribed rectangular region;
Wherein, (x
c, y
c) be target center point coordinate, (x
j,y
j) be coordinate points in rectangular area, M is counting in rectangular area, and f (x, y) represents the gray-scale value of current point.
Present invention also offers a kind of target central point quick extraction system, comprising:
Image collection module, for obtaining binary image;
Mark module, for marking connected domains all in described binary image;
Detection module, detects target connected domain for the described connected domain according to mark;
Locating module, for according to described target connected domain determination circumscribed rectangular region;
Coordinate output module, for obtaining target center point coordinate in described circumscribed rectangular region.
The present invention adopts technique scheme, has following beneficial effect:
Target central point rapid extracting method provided by the invention and system, all connected domains in acquisition binary image are marked, target connected domain is detected again according to the described connected domain of mark, according to described target connected domain determination circumscribed rectangular region, thus obtain target center point coordinate in described circumscribed rectangular region, relative to the rim detection adopted in prior art, Hessian matrix, Hough transform, matching scheduling algorithm all will carry out a large amount of multiplication and division computings, and the image binaryzation in the present invention, it is logical operation and plus and minus calculation that the computing major part of connected component labeling and centroid method belongs to, therefore execution efficiency is higher.
In addition, target central point rapid extracting method provided by the invention and system, have employed connected component labeling in zone location, do not have target restricted number; Meanwhile, the connected component labeling of employing and centroid method are not easy to change by target geometric parameter, and adaptability is good.
In addition, in terms of existing technologies, when carrying out target following location, because being subject to the interference such as air-flow, light, sometimes can there is the changes such as certain physical dimension, brightness in target, and connected component labeling used in the present invention and centroid method affect less in the picture, and reliability is high.
Again, because luminescence target target intensity profile all meets Gaussian distribution, and namely the gray scale barycenter of Central Symmetry target is geometric center, and therefore the present invention is by extracting target center point coordinate, improves precision.
Accompanying drawing explanation
Below in conjunction with the drawings and specific embodiments, the target central point rapid extracting method provide the embodiment of the present invention and beneficial effect thereof are described in detail.
The flow chart of steps of a kind of target central point rapid extracting method that Fig. 1 provides for an embodiment of the present invention;
In Fig. 2, (a) is the principle schematic of employing 4 connected component labeling method;
In Fig. 2, (b) is the principle schematic of employing 8 connected component labeling method;
The connected component labeling schematic diagram of the target that Fig. 3 provides for the embodiment of the present invention;
The dimensional Gaussian distribution schematic diagram that Fig. 4 provides for the embodiment of the present invention;
Fig. 5 is the structural representation of target central point quick extraction system provided by the invention.
Embodiment
In order to make object of the present invention, technical scheme and Advantageous Effects thereof more clear, below in conjunction with the drawings and specific embodiments, the present invention is further elaborated.Should be understood that, the embodiment described in this instructions is only used to explain the present invention, is not intended to limit the present invention.
Refer to Fig. 1, an embodiment of the present invention provides a kind of target central point rapid extracting method 100, comprises the steps:
Step S110: obtain binary image;
In the present embodiment, binary conversion treatment is carried out to the image of input.In actual applications, in order to improve the processing speed of image binaryzation, threshold value needs to provide empirical value.The empirical value of threshold value can utilize threshold value to ask for algorithm (as Otu algorithm) and calculates in advance and carry out certain artificial adjustment acquisition, or people provides and finds out suitable threshold value by experiment.That target will have the pixel of sufficient amount in the binary image obtained to the requirement of the empirical value of threshold value.Be appreciated that the pixel quantity due to targeting regions will much larger than the pixel quantity at target edge, and target gray scale is general and background gray scale has larger gap, this threshold value has between larger selection area.
Step S120: connected domains all in described binary image are marked;
In the present embodiment, carry out connected component labeling to the binary image obtained, the pixel value by different connected domain gives particular value.
Preferably, 4 connected component labeling methods and/or 8 connected component labeling methods are adopted to mark described binary image.
Refer to Fig. 2, wherein (a) is the principle schematic of employing 4 connected component labeling method, and (b) is the principle schematic of employing 8 connected component labeling method.Wherein, the 4 connected component labeling methods neighbor of upper and lower, left and right on totally 4 directions that will consider current pixel; 8 connected component labeling methods will consider upper and lower, left and right, upper left, lower-left, upper right, the bottom right neighbor on totally 8 directions.Wherein, (i, j) represents current pixel.
Step S130: the described connected domain according to mark detects target connected domain;
Preferably, according to detection criteria determination target connected domain, described detection criteria provides according to the feature of target, and the feature of described target comprises geometric configuration, physical dimension, gray distribution features.
Described geometric configuration comprises target disc, and geometric configuration criterion is that the line number of pixel in connected domain and columns are close to 1:1; Described physical dimension criterion is that the line number of pixel in connected domain and columns are all greater than 2, and described intensity profile criterion is the gray scale corresponding to connected domain is Gaussian distribution.
Be appreciated that, target connected domain detection criteria can provide according to the feature of target, there is Central Symmetry feature as target, in connected domain the line number of pixel and columns more close, therefore can judge target connected domain according to the ratio of the two (close to 1:1).
Referring to Fig. 3, is the connected component labeling schematic diagram of the target that the embodiment of the present invention provides.Wherein, grey parts is expressed as connected domain.
Step S140: according to described target connected domain determination circumscribed rectangular region;
Preferably, determine the described horizontal ordinate of target connected domain, the extreme value of ordinate according to following formula, be designated as respectively: x
min, x
max, y
min, y
max, wherein (x
i, y
i) be coordinate points in described target connected domain, N is counting in connected domain
(x
min, y
min), (x
min, y
max), (x
max, y
max), (x
max, y
min) 4 be connected to form described circumscribed rectangular region.
Be appreciated that by above-mentioned steps, the circumscribed rectangular region of described target connected domain can be determined.
Step S150: obtain target center point coordinate in described circumscribed rectangular region.
Preferably, adopt following formula, utilize gray scale centroid method to obtain target center point coordinate in described circumscribed rectangular region;
Wherein, (x
c, y
c) be target center point coordinate, (x
j, y
j) be coordinate points in rectangular area, M is counting in rectangular area, and f (x, y) represents the gray-scale value of current point.
Be appreciated that the area due to circumscribed rectangular region is generally greater than connected domain, known M>N.Here why calculate gray scale barycenter in connected domain in rectangular area, be because rectangular area contains the more complete grey scale change of target, ensure that the precision of result of calculation.
In addition, target center point coordinate in circumscribed rectangular region is obtained owing to adopting gray scale centroid method, the gray scale general satisfaction of such luminescence (comprising active illuminating and passive luminescence) target dimensional Gaussian distribution (as shown in Figure 4), known, namely gray scale barycenter is target center, thus improves precision.
Refer to Fig. 5, be the structural representation of target central point quick extraction system provided by the invention, comprise: image collection module 110, mark module 120, detection module 130, locating module 140 and coordinate output module 150.Wherein, image collection module 110 is for obtaining binary image; Mark module 120 is for marking connected domains all in described binary image; Detection module 130 detects target connected domain for the described connected domain according to mark; Locating module 140 is for according to described target connected domain determination circumscribed rectangular region; Coordinate output module 150 is for obtaining target center point coordinate in described circumscribed rectangular region.
Target central point rapid extracting method provided by the invention and system, all connected domains in acquisition binary image are marked, target connected domain is detected again according to the described connected domain of mark, according to described target connected domain determination circumscribed rectangular region, thus obtain target center point coordinate in described circumscribed rectangular region, relative to the rim detection adopted in prior art, Hessian matrix, Hough transform, matching scheduling algorithm all will carry out a large amount of multiplication and division computings, and the image binaryzation in the present invention, it is logical operation and plus and minus calculation that the computing major part of connected component labeling and centroid method belongs to, therefore execution efficiency is higher.
In addition, target central point rapid extracting method provided by the invention and system, have employed connected component labeling in zone location, do not have target restricted number; Meanwhile, the connected component labeling of employing and centroid method are not easy to change by target geometric parameter, and adaptability is good.
In addition, in terms of existing technologies, when carrying out target following location, because being subject to the interference such as air-flow, light, sometimes can there is the changes such as certain physical dimension, brightness in target, and connected component labeling used in the present invention and centroid method affect less in the picture, and reliability is high.
Again, because luminescence target target intensity profile all meets Gaussian distribution, and namely the gray scale barycenter of Central Symmetry target is geometric center, and therefore the present invention is by extracting target center point coordinate, improves precision.
The announcement of book and instruction according to the above description, those skilled in the art in the invention can also carry out suitable change and amendment to above-mentioned embodiment.Therefore, the present invention is not limited to embodiment disclosed and described above, also should fall in the protection domain of claim of the present invention modifications and changes more of the present invention.In addition, although employ some specific terms in this instructions, these terms just for convenience of description, do not form any restriction to the present invention.
Claims (8)
1. a target central point rapid extracting method, is characterized in that, comprises the steps:
Obtain binary image;
Connected domains all in described binary image are marked;
Described connected domain according to mark detects target connected domain;
According to described target connected domain determination circumscribed rectangular region;
Obtain target center point coordinate in described circumscribed rectangular region.
2. target central point rapid extracting method according to claim 1, is characterized in that, wherein, marks, comprising connected domains all in described binary image:
4 connected component labeling methods and/or 8 connected component labeling methods are adopted to mark described binary image.
3. target central point rapid extracting method according to claim 2, is characterized in that, described 4 connected component labeling methods are to the upper and lower, left and right of current pixel totally 4 the coconnected pixels imparting in direction particular values; Described 8 connected component labeling methods to the upper and lower, left and right of current pixel, upper left, lower-left, upper right, bottom right totally 8 coconnected pixels in direction give particular values.
4. target central point rapid extracting method according to claim 3, is characterized in that, wherein, the described connected domain according to mark detects target connected domain, is specially:
According to detection criteria determination target connected domain, described detection criteria provides according to the feature of target, and the feature of described target comprises geometric configuration, physical dimension, gray distribution features.
5. target central point rapid extracting method according to claim 4, it is characterized in that, described geometric configuration comprises target disc, and geometric configuration criterion is that the line number of pixel in connected domain and columns are close to 1:1; Described physical dimension criterion is that the line number of pixel in connected domain and columns are all greater than 2, and described intensity profile criterion is the gray scale corresponding to connected domain is Gaussian distribution.
6. target central point rapid extracting method according to claim 4, is characterized in that: wherein, according to described target connected domain determination circumscribed rectangular region, is specially:
Determine the described horizontal ordinate of target connected domain, the extreme value of ordinate according to following formula, be designated as respectively: x
min, x
max, y
min, y
max, wherein (x
i, y
i) be coordinate points in described target connected domain, N is counting in connected domain
(x
min, y
min), (x
min, y
max), (x
max, y
max), (x
max, y
min) 4 be connected to form described circumscribed rectangular region.
7. target central point rapid extracting method according to claim 6, is characterized in that: wherein, obtains target center point coordinate in described circumscribed rectangular region, is specially:
Adopt following formula, utilize gray scale centroid method to obtain target center point coordinate in described circumscribed rectangular region;
Wherein, (x
c, y
c) be target center point coordinate, (x
j, y
j) be coordinate points in rectangular area, M is counting in rectangular area, and f (x, y) represents the gray-scale value of current point.
8. a target central point quick extraction system, is characterized in that, comprising:
Image collection module, for obtaining binary image;
Mark module, for marking connected domains all in described binary image;
Detection module, detects target connected domain for the described connected domain according to mark;
Locating module, for according to described target connected domain determination circumscribed rectangular region;
Coordinate output module, for obtaining target center point coordinate in described circumscribed rectangular region.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510810062.3A CN105469084A (en) | 2015-11-20 | 2015-11-20 | Rapid extraction method and system for target central point |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510810062.3A CN105469084A (en) | 2015-11-20 | 2015-11-20 | Rapid extraction method and system for target central point |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN105469084A true CN105469084A (en) | 2016-04-06 |
Family
ID=55606755
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201510810062.3A Pending CN105469084A (en) | 2015-11-20 | 2015-11-20 | Rapid extraction method and system for target central point |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN105469084A (en) |
Cited By (18)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106446894A (en) * | 2016-09-27 | 2017-02-22 | 广东技术师范学院 | Method for recognizing position of spherical object based on contour |
| CN107133627A (en) * | 2017-04-01 | 2017-09-05 | 深圳市欢创科技有限公司 | Infrared light spot center point extracting method and device |
| CN107231535A (en) * | 2017-05-11 | 2017-10-03 | 大连理工大学 | A kind of space indicate thing dynamic coordinate real-time capture camera |
| CN108062770A (en) * | 2017-10-25 | 2018-05-22 | 华南农业大学 | The accurate positioning method at micropore center in a kind of microwell plate picture taken pictures naturally |
| CN108205395A (en) * | 2018-01-16 | 2018-06-26 | 安徽慧视金瞳科技有限公司 | A kind of calibration point centre coordinate precise positioning method |
| CN108572734A (en) * | 2018-04-23 | 2018-09-25 | 哈尔滨拓博科技有限公司 | A kind of gestural control system based on infrared laser associated image |
| CN109405979A (en) * | 2018-09-14 | 2019-03-01 | 中国科学院西安光学精密机械研究所 | Michelson interferometer image fringe width detection method and system |
| CN110210295A (en) * | 2019-04-24 | 2019-09-06 | 北京理工大学 | A kind of high-precision target recognition detection method under grid background |
| CN110276229A (en) * | 2018-03-14 | 2019-09-24 | 京东方科技集团股份有限公司 | Target object regional center localization method and device |
| CN110443256A (en) * | 2019-07-03 | 2019-11-12 | 大连理工大学 | A kind of extracting method in image multiple target region |
| CN112651943A (en) * | 2020-12-28 | 2021-04-13 | 南京佗道医疗科技有限公司 | Three-dimensional image mark point extraction method |
| CN112734779A (en) * | 2020-11-25 | 2021-04-30 | 深圳了然视觉科技有限公司 | Dot calibration plate edge sub-pixel detection method |
| CN112802119A (en) * | 2021-01-13 | 2021-05-14 | 北京中科慧眼科技有限公司 | Factory ranging inspection method, system and equipment based on binocular camera |
| CN113743147A (en) * | 2021-07-16 | 2021-12-03 | 广东技术师范大学 | Fuzzy imaging mechanism-based anti-fuzzy two-dimensional code image and blind restoration method thereof |
| CN114580522A (en) * | 2022-02-28 | 2022-06-03 | 中国科学院西安光学精密机械研究所 | Method for identifying multiple optical targets based on least square circle fitting method |
| CN115205317A (en) * | 2022-09-15 | 2022-10-18 | 山东高速集团有限公司创新研究院 | Bridge monitoring photoelectric target image light spot center point extraction method |
| CN115358998A (en) * | 2022-08-22 | 2022-11-18 | 法博思(宁波)半导体设备有限公司 | Method and system for acquiring point coordinates in random array picture |
| CN118374775A (en) * | 2024-06-25 | 2024-07-23 | 上海米蜂激光科技有限公司 | Control method and system for vacuum coating machine electron gun and coating monitoring system |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102509306A (en) * | 2011-10-08 | 2012-06-20 | 西安理工大学 | Specific target tracking method based on video |
| CN103164857A (en) * | 2013-03-08 | 2013-06-19 | 南京航空航天大学 | Image-based high-efficiency detection method for short-distance large-deflection circular target |
| CN103324913A (en) * | 2013-05-29 | 2013-09-25 | 长安大学 | Pedestrian event detection method based on shape features and trajectory analysis |
| CN103729632A (en) * | 2014-01-22 | 2014-04-16 | 哈尔滨工业大学 | Round Mark point positioning method based on connected region filtering |
| CN103745475A (en) * | 2014-01-22 | 2014-04-23 | 哈尔滨工业大学 | Detection and positioning method used for spherical pin element |
| CN104331695A (en) * | 2014-09-01 | 2015-02-04 | 西北工业大学 | Robust round identifier shape quality detection method |
-
2015
- 2015-11-20 CN CN201510810062.3A patent/CN105469084A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102509306A (en) * | 2011-10-08 | 2012-06-20 | 西安理工大学 | Specific target tracking method based on video |
| CN103164857A (en) * | 2013-03-08 | 2013-06-19 | 南京航空航天大学 | Image-based high-efficiency detection method for short-distance large-deflection circular target |
| CN103324913A (en) * | 2013-05-29 | 2013-09-25 | 长安大学 | Pedestrian event detection method based on shape features and trajectory analysis |
| CN103729632A (en) * | 2014-01-22 | 2014-04-16 | 哈尔滨工业大学 | Round Mark point positioning method based on connected region filtering |
| CN103745475A (en) * | 2014-01-22 | 2014-04-23 | 哈尔滨工业大学 | Detection and positioning method used for spherical pin element |
| CN104331695A (en) * | 2014-09-01 | 2015-02-04 | 西北工业大学 | Robust round identifier shape quality detection method |
Non-Patent Citations (1)
| Title |
|---|
| 董坤: "视频监控中运动人体检测与异常行为分析研究", 《中国优秀硕士学位论文全文数据库 信息科技辑》 * |
Cited By (26)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106446894A (en) * | 2016-09-27 | 2017-02-22 | 广东技术师范学院 | Method for recognizing position of spherical object based on contour |
| CN106446894B (en) * | 2016-09-27 | 2019-04-12 | 广东技术师范学院 | A method of based on outline identification ball-type target object location |
| CN107133627A (en) * | 2017-04-01 | 2017-09-05 | 深圳市欢创科技有限公司 | Infrared light spot center point extracting method and device |
| WO2018176938A1 (en) * | 2017-04-01 | 2018-10-04 | 深圳市欢创科技有限公司 | Method and device for extracting center of infrared light spot, and electronic device |
| US10719954B2 (en) | 2017-04-01 | 2020-07-21 | Shenzhen Camsense Technologies Co., Ltd | Method and electronic device for extracting a center position of an infrared spot |
| CN107231535A (en) * | 2017-05-11 | 2017-10-03 | 大连理工大学 | A kind of space indicate thing dynamic coordinate real-time capture camera |
| CN107231535B (en) * | 2017-05-11 | 2020-02-18 | 大连理工大学 | Real-time camera of catching of space marker dynamic coordinate |
| CN108062770A (en) * | 2017-10-25 | 2018-05-22 | 华南农业大学 | The accurate positioning method at micropore center in a kind of microwell plate picture taken pictures naturally |
| CN108205395A (en) * | 2018-01-16 | 2018-06-26 | 安徽慧视金瞳科技有限公司 | A kind of calibration point centre coordinate precise positioning method |
| CN108205395B (en) * | 2018-01-16 | 2021-03-23 | 安徽慧视金瞳科技有限公司 | Method for accurately positioning center coordinates of calibration points |
| CN110276229A (en) * | 2018-03-14 | 2019-09-24 | 京东方科技集团股份有限公司 | Target object regional center localization method and device |
| CN108572734A (en) * | 2018-04-23 | 2018-09-25 | 哈尔滨拓博科技有限公司 | A kind of gestural control system based on infrared laser associated image |
| CN109405979B (en) * | 2018-09-14 | 2019-11-15 | 中国科学院西安光学精密机械研究所 | Michelson interferometer image fringe width detection method and system |
| CN109405979A (en) * | 2018-09-14 | 2019-03-01 | 中国科学院西安光学精密机械研究所 | Michelson interferometer image fringe width detection method and system |
| CN110210295A (en) * | 2019-04-24 | 2019-09-06 | 北京理工大学 | A kind of high-precision target recognition detection method under grid background |
| CN110443256A (en) * | 2019-07-03 | 2019-11-12 | 大连理工大学 | A kind of extracting method in image multiple target region |
| CN112734779A (en) * | 2020-11-25 | 2021-04-30 | 深圳了然视觉科技有限公司 | Dot calibration plate edge sub-pixel detection method |
| CN112651943A (en) * | 2020-12-28 | 2021-04-13 | 南京佗道医疗科技有限公司 | Three-dimensional image mark point extraction method |
| CN112802119A (en) * | 2021-01-13 | 2021-05-14 | 北京中科慧眼科技有限公司 | Factory ranging inspection method, system and equipment based on binocular camera |
| CN113743147A (en) * | 2021-07-16 | 2021-12-03 | 广东技术师范大学 | Fuzzy imaging mechanism-based anti-fuzzy two-dimensional code image and blind restoration method thereof |
| CN113743147B (en) * | 2021-07-16 | 2023-08-29 | 广东技术师范大学 | Anti-fuzzy two-dimensional code image based on fuzzy imaging mechanism and blind restoration method thereof |
| CN114580522A (en) * | 2022-02-28 | 2022-06-03 | 中国科学院西安光学精密机械研究所 | Method for identifying multiple optical targets based on least square circle fitting method |
| CN114580522B (en) * | 2022-02-28 | 2023-08-11 | 中国科学院西安光学精密机械研究所 | Method for identifying multiple optical targets based on least square circle fitting method |
| CN115358998A (en) * | 2022-08-22 | 2022-11-18 | 法博思(宁波)半导体设备有限公司 | Method and system for acquiring point coordinates in random array picture |
| CN115205317A (en) * | 2022-09-15 | 2022-10-18 | 山东高速集团有限公司创新研究院 | Bridge monitoring photoelectric target image light spot center point extraction method |
| CN118374775A (en) * | 2024-06-25 | 2024-07-23 | 上海米蜂激光科技有限公司 | Control method and system for vacuum coating machine electron gun and coating monitoring system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105469084A (en) | Rapid extraction method and system for target central point | |
| CN103727930B (en) | A kind of laser range finder based on edge matching and camera relative pose scaling method | |
| CN103530590B (en) | DPM Quick Response Code recognition system | |
| CN106251353A (en) | Weak texture workpiece and the recognition detection method and system of three-dimensional pose thereof | |
| CN102354457B (en) | General Hough transformation-based method for detecting position of traffic signal lamp | |
| CN103593695B (en) | A kind of method of DPM two-dimension code area location | |
| CN102096821A (en) | Number plate identification method under strong interference environment on basis of complex network theory | |
| CN109325935A (en) | A kind of transmission line faultlocating method based on unmanned plane image | |
| CN103793708A (en) | Multi-scale license plate precise locating method based on affine correction | |
| CN103413303A (en) | Infrared target segmentation method based on joint obviousness | |
| CN104537342B (en) | A kind of express lane line detecting method of combination ridge border detection and Hough transformation | |
| CN104851089A (en) | Static scene foreground segmentation method and device based on three-dimensional light field | |
| CN105096298A (en) | Grid feature point extraction method based on fast line extraction | |
| CN102789578A (en) | Infrared remote sensing image change detection method based on multi-source target characteristic support | |
| CN111382658B (en) | Road traffic sign detection method in natural environment based on image gray gradient consistency | |
| CN104899892A (en) | Method for quickly extracting star points from star images | |
| CN103544489A (en) | Device and method for locating automobile logo | |
| CN103714547A (en) | Image registration method combined with edge regions and cross-correlation | |
| CN103913166A (en) | Star extraction method based on energy distribution | |
| Li et al. | Judgment and optimization of video image recognition in obstacle detection in intelligent vehicle | |
| CN104915642A (en) | Method and apparatus for measurement of distance to vehicle ahead | |
| Wang et al. | Fast vanishing point detection method based on road border region estimation | |
| Gu et al. | Vision-based multi-scaled vehicle detection and distance relevant mix tracking for driver assistance system | |
| CN103093241B (en) | Based on the remote sensing image nonuniformity cloud layer method of discrimination of homogeneity process | |
| CN105354610A (en) | Random Hough transform-based people counting 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 | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20160406 |