CN106841673A - A kind of river surface mean flow rate measurement apparatus and method - Google Patents
A kind of river surface mean flow rate measurement apparatus and method Download PDFInfo
- Publication number
- CN106841673A CN106841673A CN201710030722.5A CN201710030722A CN106841673A CN 106841673 A CN106841673 A CN 106841673A CN 201710030722 A CN201710030722 A CN 201710030722A CN 106841673 A CN106841673 A CN 106841673A
- Authority
- CN
- China
- Prior art keywords
- motion
- current time
- river surface
- certain hour
- flow rate
- 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
- G01—MEASURING; TESTING
- G01P—MEASURING LINEAR OR ANGULAR SPEED, ACCELERATION, DECELERATION, OR SHOCK; INDICATING PRESENCE, ABSENCE, OR DIRECTION, OF MOVEMENT
- G01P5/00—Measuring speed of fluids, e.g. of air stream; Measuring speed of bodies relative to fluids, e.g. of ship, of aircraft
- G01P5/18—Measuring speed of fluids, e.g. of air stream; Measuring speed of bodies relative to fluids, e.g. of ship, of aircraft by measuring the time taken to traverse a fixed distance
Landscapes
- Engineering & Computer Science (AREA)
- Aviation & Aerospace Engineering (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Image Analysis (AREA)
Abstract
The present invention provides a kind of method and system of the mean flow rate for measuring river surface, and methods described includes：River surface image based on current time and previous moment, obtains the motion conspicuousness point or motion salient region of the river surface image at current time；Motion conspicuousness point or motion salient region based on each moment in certain hour, obtain the average displacement in certain hour；And based on than the average displacement and inter frame temporal in chi calibration coefficient, the certain hour, obtain the mean flow rate in certain hour.The present invention need not throw buoy, and sustainable flow-speed measurement flow velocity in the water surface.
Description
Technical field
The present invention relates to image processing field, more particularly, to river surface mean flow rate measurement apparatus and method.
Background technology
The river of China is numerous, for the comprehensive utilization in river, always in occupation of China's national economy and social development
Critical role.Hydrologic monitoring information plays an important roll to preventing treatment flood and bloods and droughts and Water Resource Adjustment And Control.And flow
Speed measurement is one of important process of hydrologic monitoring, but current flow-speed measurement method aspect has certain limitation.
Conventional river flow velocity measuring method is broadly divided into 3 classes.
The first kind is traditional current meter mensuration, and its cardinal principle is to drive rotation oar to rotate by current, record rotation oar
Rotating speed, flow velocity can be calculated by certain mapping relations, but is existed and worked as water quality mutation, and silt content becomes big time error and can become big,
And water float thing can influence its result even to damage the problem of rotating plasma.
Equations of The Second Kind is to measure flow velocity by acoustical Doppler effect, is mainly used in surveying vessel, there is also equipment and people
Class input ratio is larger, cost problem higher.
3rd class is the water flow speed measurement method combined with float technique based on Video processing, the movement locus of buoy in frequency
Water velocity is calculated with reference to camera calibration.
Two examples of the 3rd class method are：(1) patent of invention " large-range surface flow rate image processing system long and its
Synchronous real-time measurement method " (application number CN1289037A, 2000), (2) " river flow velocity monitoring system based on Video processing
Design " (Han Yuwan, Institutes Of Technology Of Taiyuan's Master's thesis, 2010).Two examples have used float technique with image procossing phase
With reference to scheme, need when in use put into buoy, then in video tracking buoy or trace particle motion.The two examples
In son, the following principle of use is all based on buoy has significantly different with the water surface in color, and with the water surface as background, buoy is tracking
Target.But the method is needed to buoy is thrown in camera field of view, after buoy drifts out the visual field of video camera, just cannot detection stream
Speed, it is impossible to realize the uninterrupted real-time measurement to water velocity；The throwing of buoy simultaneously and recovery are also pretty troublesome thing.
The content of the invention
The present invention provides a kind of river surface mean flow for overcoming above mentioned problem or solving the above problems at least in part
Speed measuring device and method.
According to an aspect of the present invention, there is provided it is a kind of measure river surface mean flow rate method, including：
S1, the river surface image based on current time and previous moment, obtain the river surface image at current time
Motion conspicuousness point or motion salient region；
S2, the motion conspicuousness point based on each moment in certain hour or motion salient region, obtain certain hour
Interior average displacement；And
S3, based on than the average displacement and inter frame temporal in chi calibration coefficient, the certain hour, obtain certain hour
Interior mean flow rate.
According to another aspect of the present invention, a kind of system for measuring river surface mean flow rate is also provided, including：
Motion conspicuousness detection means, for the river surface image based on current time and previous moment, obtains current
The motion conspicuousness point or motion salient region of the river surface image at moment；
Average displacement detection means, was connected, based on each moment in certain hour with the motion conspicuousness detection means
Motion conspicuousness point or motion salient region, obtain certain hour in average displacement；And
Mean flow rate detection means, is connected with the average displacement detection means, and the mean flow rate detection means is used for
Based on average displacement and inter frame temporal than each moment in chi calibration coefficient and certain hour, obtain flat in certain hour
Equal flow velocity.
The application obtains river video, the analysis wherein feature with notable motility by perpendicular to the camera of the water surface
Figure, extracts motion salient region therein or motion conspicuousness point, tracks each motion salient region or motion conspicuousness
The corresponding displacement of point, simultaneous image coordinate system and calculates with the position mapping relations and inter frame temporal of realistic space coordinate system
River surface actual flow velocity.The application need not throw buoy in the water surface, but itself can be produced using during river flow
Fluctuation textural characteristics or natural floating object come flow-speed measurement flow velocity that measure river surface mean flow rate and sustainable.
Brief description of the drawings
Fig. 1 is a kind of method flow diagram of the mean flow rate of the measurement river surface according to the embodiment of the present invention；
Fig. 2 is the histogram of the method for the mean flow rate of the measurement river surface according to the embodiment of the present invention；
Fig. 3 is the structured flowchart of the system of the measurement river surface mean flow rate according to the embodiment of the present invention.
Specific embodiment
With reference to the accompanying drawings and examples, specific embodiment of the invention is described in further detail.Hereinafter implement
Example is not limited to the scope of the present invention for illustrating the present invention.
Buoy is thrown on the water surface in order to overcome need in the prior art, it is caused video camera is drifted out when buoy visual field after
The problem of flow velocity cannot be detected, and is thrown and is reclaimed troublesome problem, river flow process is utilized the invention provides one kind
In fluctuation textural characteristics itself that produce or nature floating object come flow-speed measurement that measure river surface mean flow rate and sustainable
The method of flow velocity.
Fig. 1 shows a kind of method flow diagram of the mean flow rate of measurement river surface according to embodiments of the present invention, bag
Include：
S1, the river surface image based on current time and previous moment, obtain the river surface image at current time
Motion conspicuousness point or motion salient region；
S2, the motion conspicuousness point based on each moment in certain hour or motion salient region, obtain certain hour
Interior average displacement；And
S3, based on than the average displacement and inter frame temporal in chi calibration coefficient, the certain hour, obtain certain hour
Interior mean flow rate.
The present invention obtains river video (sequence image) by perpendicular to the camera of the water surface, and analysis wherein has significantly fortune
The characteristic pattern of dynamic property, extracts motion significant characteristics point therein, tracks the corresponding pixel position of each motion significant characteristics point
Move, simultaneous image coordinate system and calculate river surface reality with the position mapping relations and inter frame temporal of realistic space coordinate system
Border flow velocity.
In one embodiment, the invention provides a kind of method for obtaining average displacement based on motion salient region,
Wherein, the step S1 includes：
S1.1, the river surface image P based on ttWith the river surface image P at t-1 momentt-1Frame it is poor, obtain t
The motion significant characteristics figure x at momentt.Similarly, the river surface image P based on the t+1 momentt+1With the river surface figure of t
As Pt, obtain the motion significant characteristics figure x at t+1 momentt+1。
Frame is poor, also referred to as inter-frame difference, be it is a kind of by adjacent two frame in sequence of video images made calculus of differences come
The method for obtaining moving target profile, it can be perfectly suitable for the situation that there are multiple moving targets and video camera movement.
When occurring abnormal object of which movement in monitoring scene, more obvious difference occurs between frame and frame, two frames subtract each other, and obtain two
The absolute value of two field picture luminance difference, judges whether it analyzes the kinetic characteristic of video or image sequence more than threshold value, it is determined that figure
As whetheing there is object of which movement in sequence.
S1.2, the motion significant characteristics figure based on the current time, obtain the river surface image at current time
Motion salient region.
In one embodiment, the step S1.2 includes：
S1.2.1, the motion significant characteristics figure binaryzation by t, obtain binary map.The binaryzation of image, being exactly will
The gray value of the pixel on image is set to 0 or 255, that is, whole image is showed into significantly only black and white regarding
Feel effect.Most common method is exactly to set a threshold value T, and the data of image are divided into two parts with T：Pixel group more than T
With the pixel group less than T.
S1.2.2, in the binary map choose Nt,1Individual connected domain, any one of connected domain is that length or width are
The rectangle of 20-100 pixels.The most important method of binary image analysis is exactly connected component labeling, and it is all bianry images
The basis of analysis, it allows each single connected region to form one by the mark to white pixel in bianry image (target)
Individual identified block, as connected domain.
S1.2.3, using the connected domain as masking-out, masking-out is exactly to select the outside of frame (inside for selecting frame is exactly constituency), is looked into
Look for the position of the correspondence connected domain in the motion significant characteristics figure of t, as the motion salient region, these fortune
The set of dynamic salient region is designated as { ft,i(i=1,2 ..., Nt,1| t=1,2 ...).
In one embodiment, the threshold value of the binaryzation is the gray scale maximum of the motion significant characteristics figure
0.9 times.
In one embodiment, the step S2 includes：
S2.1, in the significant characteristics figure of t search with the t-1 moment each move salient region match
With region；
S2.2, the calculating matching area are in the relative displacement in significant characteristics figure is moved of t-1 moment to t；With
And
S2.3, the relative displacement based on corresponding matching area of each moment in certain hour, obtain the straight of relative displacement
Fang Tu, to the average value of the value in a range of region near peak value in the histogram and peak value, as described one timing
Interior average displacement.
For a template ft,iIf, can be in motion significant characteristics figure xt+1In search its matching area, calculate this
With area coordinate and ft,iIn xtThe relative displacement of middle coordinate, if all in xt+1It is middle can find matching area template number be
Nt,2, then the relative displacement set { s of each motion salient region is obtainedt+1,j(i=1,2 ..., Nt,2| t=1,2 ...).
In one embodiment, present invention also offers a kind of method for obtaining average displacement based on motion conspicuousness point,
Wherein, the step S1 includes：
S1.1, the river surface image based on t and t-1 moment frame it is poor, obtain current time motion conspicuousness
Characteristic pattern；
S1.2, based on corner detection approach (such as Harris operators), detect the key point in the motion significant characteristics figure,
The motion conspicuousness point of t is obtained, its set is designated as { ft,i(i=1,2 ..., Nt,1| t=1,2 ...).
In one embodiment, the step S2 includes：
The sift of motion conspicuousness point is special described in S2.1, the motion significant characteristics figure to each moment in certain hour
Levy, the point of the sift characteristic matchings of the motion conspicuousness point at search and t-1 moment from the motion conspicuousness point of t, as
Match point.
In one embodiment, denoising Processing (as using Ransac algorithms) is carried out for the match point, removes mistake
The match point of matching, retains correct match point.
S2.2, the match point is calculated in the relative displacement in significant characteristics figure is moved of t-1 moment to t, if institute
Have in xtIn can find match point number for Nt,m, then the relative displacement set { s that t respectively moves conspicuousness point is obtainedt,k}(k
=1,2 ..., Nt,m| t=1,2 ...).
S2.3, the relative displacement based on corresponding match point of each moment in certain hour, obtain the Nogata of relative displacement
Figure, to the average value of the value in a range of region near peak value in the histogram and peak value, as in certain hour
Average displacement.
In one embodiment, the step S3 includes：Obtained within a period of time many moment match point or
Displacement with region, then makes the histogram of these displacements, it will usually form a unimodal figure, we find peak value
The position of (p), herein is in being calculated the region that displacement is most concentrated in a period of time.But we are still considered outside p
Contribution of the displacement to overall average displacement, segment limit (± ⊿ p can be taken around p), that is, take interval [p- ⊿ p, p+ ⊿ p], will
All interframe displacements displacement within this range is completely added up averagely in calculating the time period, that is, average displacement is the total of calculation
Average displacement, the error for so contributing to the matching error for eliminating some interframe during subsequently with template matching method to cause.
Fig. 2 shows the histogram in the embodiment of the present invention, and abscissa is the displacement in units of pixel, ordinate in figure
It is the region quantity in certain displacement.Figure it is seen that the region quantity that displacement is piled up when being 27 pixels or so is at most,
Therefore it is considered as peak value by 27, a scope is taken around it, such as ± 5 pixels, then only the displacement in the range of [22,32] is carried out
Averagely, the average displacement in a period of time can be calculated.Find out that some displacements are very big (as 43 is later) in Fig. 2, I
Be regarded as what the erroneous matching in template matches was caused, or noise.
In one embodiment, also include before the step S3；
Based on camera distance, camera angle and shooting focal length, obtain described than chi calibration coefficient：
fn=z/af
Wherein, fnIt is that, than chi calibration coefficient, z is distance of the camera lens focus to the water surface, α is imaging plane to image
The multiplication factor of plane, f is the focal length of camera lens.
In one embodiment, the average displacement based on than each moment in chi calibration coefficient and certain hour and
Inter frame temporal, the calculation expression of mean flow rate obtained in certain hour is：
Wherein, fn be than chi calibration coefficient,It is average displacement, △ t are inter frame temporal, and v is average stream flow superficial velocity.
Fig. 3 shows a kind of structured flowchart of system for measuring river surface mean flow rate of the invention, including：
Motion conspicuousness detection means, for the river surface image based on current time and previous moment, obtains current
The motion conspicuousness point or motion salient region of the river surface image at moment；
Average displacement detection means, was connected, based on each moment in certain hour with the motion conspicuousness detection means
Motion conspicuousness point or motion salient region, obtain certain hour in average displacement；And
Mean flow rate detection means, is connected with the average displacement detection means, and the mean flow rate detection means is used for
Based on average displacement and inter frame temporal than each moment in chi calibration coefficient and certain hour, obtain flat in certain hour
Equal flow velocity.
In one embodiment, the motion conspicuousness detection means includes：
Characteristic pattern generation module, it is poor for the frame based on current time and the river surface image of previous moment, worked as
The motion significant characteristics figure at preceding moment；And
Conspicuousness detection module, is connected with the characteristic pattern generation module, and the conspicuousness detection module is based on described working as
The motion significant characteristics figure at preceding moment, obtains the motion salient region of the river surface image at current time.
In one embodiment, the average displacement detection means includes：
Matching area checks module, is connected with the characteristic pattern generation module and conspicuousness detection module, the Matching band
Domain checks that module is used for each motion salient region of search and previous moment in the significant characteristics figure at current time
The matching area matched somebody with somebody；
Relative displacement computing module, checks that module is connected with the matching area, and the relative displacement computing module is used for
The matching area is calculated in the relative displacement in significant characteristics figure is moved of previous moment to current time；And
Average displacement computing module, based on the relative displacement of corresponding matching area of each moment in certain hour, obtains
The histogram of relative displacement, to the average value of the value in a range of region near peak value in the histogram and peak value, makees
It is the average displacement in the certain hour.
In one embodiment, river surface image is, in the case where level meter is combined, the primary optical axis of video camera to be hung down
It is straight to shoot in the water surface and alignment lenses river.
In one embodiment, camera lens focus to the distance of the water surface is obtained by microwave ranger.
Finally, the present processes are only preferably embodiment, are not intended to limit the scope of the present invention.It is all
Within the spirit and principles in the present invention, any modification, equivalent substitution and improvements made etc. should be included in protection of the invention
Within the scope of.
Claims (10)
1. it is a kind of measure river surface mean flow rate method, it is characterised in that including：
S1, the river surface image based on current time and previous moment, obtain the motion of the river surface image at current time
Conspicuousness point or motion salient region；
S2, the motion conspicuousness point based on each moment in certain hour or motion salient region, obtain in certain hour
Average displacement；And
S3, based on than the average displacement and inter frame temporal in chi calibration coefficient, the certain hour, obtain in certain hour
Mean flow rate.
2. the method for measuring river surface mean flow rate as claimed in claim 1, it is characterised in that the step S1 includes：
S1.1, the river surface image based on current time and previous moment frame it is poor, obtain current time motion conspicuousness
Characteristic pattern；And
S1.2, the motion significant characteristics figure based on the current time, obtain the motion of the river surface image at current time
Salient region.
3. the method for measuring river surface mean flow rate as claimed in claim 2, it is characterised in that the step S1.2 bags
Include：
S1.2.1, the motion significant characteristics figure binaryzation by current time, obtain binary map；
S1.2.2, several connected domains are chosen in the binary map, any one of connected domain is length or width is 20-
The rectangle of 100 pixels；And
S1.2.3, using the connected domain as masking-out, search the correspondence connection in the motion significant characteristics figure at current time
The position in domain, as the motion salient region.
4. the method for measuring river surface mean flow rate as claimed in claim 3, it is characterised in that the step S2 includes：
S2.1, in the significant characteristics figure at current time search with previous moment each move salient region match
With region；
S2.2, the calculating matching area are in the relative displacement in significant characteristics figure is moved of previous moment to current time；With
And
S2.3, the relative displacement based on corresponding matching area of each moment in certain hour, obtain the histogram of relative displacement,
To the average value of the value in a range of region near peak value in the histogram and peak value, as in the certain hour
Average displacement.
5. the method for measuring river surface mean flow rate as claimed in claim 1, it is characterised in that the step S1 includes：
S1.1, the river surface image based on current time and previous moment frame it is poor, obtain current time motion conspicuousness
Characteristic pattern；
S1.2, based on corner detection approach, detect the key point in the motion significant characteristics figure, obtain the fortune at the moment
Dynamic conspicuousness point.
6. the method for measuring river surface mean flow rate as claimed in claim 5, it is characterised in that the step S2 includes：
The sift features of motion conspicuousness point described in S2.1, the motion significant characteristics figure to each moment in certain hour,
The point of the sift characteristic matchings of the motion conspicuousness point of search and previous moment from the motion conspicuousness point at current time, as
Match point；
S2.2, the calculating match point are in the relative displacement in significant characteristics figure is moved of previous moment to current time；And
S2.3, the relative displacement based on corresponding match point of each moment in certain hour, obtain the histogram of relative displacement, right
The average value of the value in peak value and the neighbouring a range of region of peak value in the histogram, as the average bit in certain hour
Move.
7. the method for measuring river surface mean flow rate as claimed in claim 1, it is characterised in that before the step S3 also
Including：
Based on camera distance, camera angle and shooting focal length, obtain described than chi calibration coefficient.
8. it is a kind of measure river surface mean flow rate system, it is characterised in that including：
Motion conspicuousness detection means, for the river surface image based on current time and previous moment, obtains current time
River surface image motion conspicuousness point or motion salient region；
Average displacement detection means, is connected, the fortune based on each moment in certain hour with the motion conspicuousness detection means
Dynamic conspicuousness point or motion salient region, obtain the average displacement in certain hour；And
Mean flow rate detection means, is connected with the average displacement detection means, and the mean flow rate detection means is used to be based on
Than the average displacement and inter frame temporal at each moment in chi calibration coefficient and certain hour, the mean flow in certain hour is obtained
Speed.
9. the system for measuring river surface mean flow rate as claimed in claim 8, it is characterised in that the motion conspicuousness inspection
Surveying device includes：
Characteristic pattern generation module, it is poor for the frame based on current time and the river surface image of previous moment, when obtaining current
The motion significant characteristics figure at quarter；And
Conspicuousness detection module, is connected with the characteristic pattern generation module, when the conspicuousness detection module is based on described current
The motion significant characteristics figure at quarter, obtains the motion salient region of the river surface image at current time.
10. the system for measuring river surface mean flow rate as claimed in claim 9, it is characterised in that the average displacement inspection
Surveying device includes：
Matching area checks module, is connected with the characteristic pattern generation module and conspicuousness detection module, the matching area inspection
Look into what module was matched for the search in the significant characteristics figure at current time with each motion salient region of previous moment
Matching area；
Relative displacement computing module, checks that module is connected with the matching area, and the relative displacement computing module is used to calculate
The matching area is in the relative displacement in significant characteristics figure is moved of previous moment to current time；And
Average displacement computing module, based on the relative displacement of corresponding matching area of each moment in certain hour, obtains relative
The histogram of displacement, to the average value of the value in a range of region near peak value in the histogram and peak value, as institute
State the average displacement in certain hour.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710030722.5A CN106841673A (en) | 2017-01-16 | 2017-01-16 | A kind of river surface mean flow rate measurement apparatus and method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710030722.5A CN106841673A (en) | 2017-01-16 | 2017-01-16 | A kind of river surface mean flow rate measurement apparatus and method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN106841673A true CN106841673A (en) | 2017-06-13 |
Family
ID=59123284
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710030722.5A Pending CN106841673A (en) | 2017-01-16 | 2017-01-16 | A kind of river surface mean flow rate measurement apparatus and method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106841673A (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110187142A (en) * | 2019-06-13 | 2019-08-30 | 上海彩虹鱼海洋科技股份有限公司 | Flow monitoring method and system |
| CN110632339A (en) * | 2019-10-09 | 2019-12-31 | 天津天地伟业信息系统集成有限公司 | Water flow testing method of video flow velocity tester |
| CN113077488A (en) * | 2021-04-02 | 2021-07-06 | 昆明理工大学 | River surface flow velocity detection method and device |
| CN113822909A (en) * | 2021-09-30 | 2021-12-21 | 中科(厦门)数据智能研究院 | Water flow velocity measurement method based on motion enhancement features |
| CN116679080A (en) * | 2023-05-30 | 2023-09-01 | 广州伏羲智能科技有限公司 | River surface flow velocity determining method and device and electronic equipment |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN202502107U (en) * | 2012-03-20 | 2012-10-24 | 河海大学 | River water surface flow rate monitoring device based on feature tracking |
| CN104036522A (en) * | 2014-04-16 | 2014-09-10 | 嘉兴博海信息科技有限公司 | Water flowing speed monitoring method based on moving target identification in videos |
| CN104777327A (en) * | 2015-03-17 | 2015-07-15 | 河海大学 | Time-space image speed measuring system and method based on auxiliary laser calibration |
-
2017
- 2017-01-16 CN CN201710030722.5A patent/CN106841673A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN202502107U (en) * | 2012-03-20 | 2012-10-24 | 河海大学 | River water surface flow rate monitoring device based on feature tracking |
| CN104036522A (en) * | 2014-04-16 | 2014-09-10 | 嘉兴博海信息科技有限公司 | Water flowing speed monitoring method based on moving target identification in videos |
| CN104777327A (en) * | 2015-03-17 | 2015-07-15 | 河海大学 | Time-space image speed measuring system and method based on auxiliary laser calibration |
Non-Patent Citations (1)
| Title |
|---|
| 李刚: "基于图像处理的山溪性河流流速测量研究", 《中国优秀硕士学位论文全文数据库 信息科技辑》 * |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110187142A (en) * | 2019-06-13 | 2019-08-30 | 上海彩虹鱼海洋科技股份有限公司 | Flow monitoring method and system |
| CN110632339A (en) * | 2019-10-09 | 2019-12-31 | 天津天地伟业信息系统集成有限公司 | Water flow testing method of video flow velocity tester |
| CN113077488A (en) * | 2021-04-02 | 2021-07-06 | 昆明理工大学 | River surface flow velocity detection method and device |
| CN113077488B (en) * | 2021-04-02 | 2022-07-01 | 昆明理工大学 | River surface flow velocity detection method and device |
| CN113822909A (en) * | 2021-09-30 | 2021-12-21 | 中科(厦门)数据智能研究院 | Water flow velocity measurement method based on motion enhancement features |
| CN113822909B (en) * | 2021-09-30 | 2023-12-08 | 中科(厦门)数据智能研究院 | Water flow velocity measurement method based on motion enhancement features |
| CN116679080A (en) * | 2023-05-30 | 2023-09-01 | 广州伏羲智能科技有限公司 | River surface flow velocity determining method and device and electronic equipment |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106841673A (en) | A kind of river surface mean flow rate measurement apparatus and method | |
| CN106683121A (en) | Robust object tracking method in fusion detection process | |
| Pless et al. | Detecting independent motion: The statistics of temporal continuity | |
| CN105488811B (en) | A kind of method for tracking target and system based on concentration gradient | |
| Shafie et al. | Motion detection techniques using optical flow | |
| Pan et al. | Robust and accurate object tracking under various types of occlusions | |
| KR101051389B1 (en) | Adaptive background-based object detection and tracking device and method | |
| CN108765455A (en) | A kind of target tenacious tracking method based on TLD algorithms | |
| CN102609945A (en) | Automatic registration method of visible light and thermal infrared image sequences | |
| Ince et al. | Geometry-based estimation of occlusions from video frame pairs | |
| White et al. | An iterative pose estimation algorithm based on epipolar geometry with application to multi-target tracking | |
| Zhen et al. | Design and evaluation of an FFT-based space-time image velocimetry (STIV) for time-averaged velocity measurement | |
| CN105869108B (en) | A kind of method for registering images in the mobile target detecting of moving platform | |
| CN110264498A (en) | A kind of human body tracing method under video monitoring scene | |
| Hayet et al. | A modular multi-camera framework for team sports tracking | |
| CN111881837A (en) | Video SAR moving target detection method based on shadow extraction | |
| Walha et al. | Moving object detection system in aerial video surveillance | |
| Cao et al. | River surface velocity estimation using optical flow velocimetry improved with attention mechanism and position encoding | |
| Zhang et al. | An IR and visible image sequence automatic registration method based on optical flow | |
| Ito et al. | Seeing farther than supervision: Self-supervised depth completion in challenging environments | |
| Nong et al. | ASL-SLAM: An asynchronous formulation of lines for SLAM with Event Sensors | |
| Kumar et al. | Computer vision based moving object detection and tracking | |
| Guo et al. | Research on the detection and tracking technology of moving object in video images | |
| Wu et al. | A hierarchical estimator for object tracking | |
| Gu | An automatic target image mosaic algorithm |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20170613 |