CN106960445A - A kind of cloud motion vector calculating method based on pyramid light stream - Google Patents
A kind of cloud motion vector calculating method based on pyramid light stream Download PDFInfo
- Publication number
- CN106960445A CN106960445A CN201710205760.XA CN201710205760A CN106960445A CN 106960445 A CN106960445 A CN 106960445A CN 201710205760 A CN201710205760 A CN 201710205760A CN 106960445 A CN106960445 A CN 106960445A
- Authority
- CN
- China
- Prior art keywords
- characteristic point
- cloud layer
- layer image
- frame
- vector
- 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
- 238000000034 method Methods 0.000 title claims abstract description 25
- 150000003839 salts Chemical class 0.000 claims abstract description 11
- 230000003287 optical effect Effects 0.000 claims abstract description 7
- 238000001914 filtration Methods 0.000 claims description 6
- 238000009499 grossing Methods 0.000 description 3
- 230000001154 acute effect Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 238000000205 computational method Methods 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000002360 preparation method Methods 0.000 description 1
- 230000000717 retained effect Effects 0.000 description 1
- 238000012163 sequencing technique Methods 0.000 description 1
Classifications
-
- G06T5/70—
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20024—Filtering details
- G06T2207/20032—Median filtering
Abstract
The invention discloses a kind of cloud motion vector calculating method based on pyramid light stream, this method includes:S1:Two frame cloud layer images are continuously captured by the camera for vertically shooting ground;S2:Detect multiple characteristic points of the first frame cloud layer image;S3:Two frame cloud layer images are compared using pyramid optical flow method, position of each characteristic point in the second frame cloud layer image is estimated;S4:Judge whether position of each characteristic point in the first frame cloud layer image changes relative to the position in the second frame cloud layer image;S5:If do not changed, corresponding characteristic point is filtered out, otherwise retains corresponding characteristic point;S6:The vector for obtaining each characteristic point is calculated according to position of the characteristic point of each reservation in two frame cloud layer images;S7:According to characteristic point with a grain of salt Vector operation obtain characteristic point with a grain of salt resultant vector.The present invention can accurately calculate the vector of cloud motion.
Description
Technical field
The present invention relates to cloud motion detection technical field, more particularly to a kind of cloud motion vector based on pyramid light stream
Computational methods.
Background technology
The prediction of cloud motion is one of vital task of GMS observation, the distance of Accurate Prediction cloud motion and side
To the size and Orientation of air-out can be derived, so as to the weather that forecasts with unerring accuracy.Because the vector of cloud motion is in synoptic analysis
It is important information in terms of forecast, aeronautical meteorology, it is therefore necessary to which cloud motion vector is accurately calculated.However, existing
Technology does not carry out the research of this respect also.
The content of the invention
The present invention solves the technical problem of a kind of cloud motion vector calculating method based on pyramid light stream of offer,
The vector of cloud motion can accurately be calculated.
In order to solve the above technical problems, one aspect of the present invention is:There is provided a kind of based on pyramid light stream
Cloud motion vector calculating method, comprise the following steps:S1:Two frame cloud layers are continuously captured by the camera for vertically shooting ground
Image;S2:Detect multiple characteristic points of the first frame cloud layer image in the two frames cloud layer image;S3:Use pyramid optical flow method
The two frames cloud layer image is compared, each characteristic point second frame cloud layer in the two frames cloud layer image is estimated
Position in image;S4:Judge position of each characteristic point in the first frame cloud layer image relative in second frame
Whether the position in cloud layer image changes;S5:If do not changed, corresponding characteristic point is filtered out, if hair
It is raw to change, then retain corresponding characteristic point;S6:Calculated according to position of the characteristic point of each reservation in two frame cloud layer images
Obtain the vector of each characteristic point;S7:According to characteristic point with a grain of salt Vector operation obtain characteristic point with a grain of salt
Resultant vector.
Wherein, before step S2, methods described also includes:The two frames cloud layer image is put down using medium filtering
Sliding processing.
The beneficial effects of the invention are as follows:The situation of prior art is different from, the method for the embodiment of the present invention uses pyramid
Optical flow method carries out feature point tracking to adjacent two frames cloud layer image, obtains the feature that position changes in two frame cloud layer images
Point, the Vector operation resultant vector to these characteristic points can obtain cloud motion vector, so as to the accurate vector for calculating cloud motion.
Brief description of the drawings
Fig. 1 is the schematic flow sheet of cloud motion vector calculating method of the embodiment of the present invention based on pyramid light stream.
Specific embodiment
Below in conjunction with the accompanying drawing in the embodiment of the present invention, the technical scheme in the embodiment of the present invention is carried out clear, complete
Site preparation is described, it is clear that described embodiment is only a part of embodiment of the present invention, rather than whole embodiments.It is based on
Embodiment in the present invention, it is every other that those of ordinary skill in the art are obtained under the premise of creative work is not made
Embodiment, belongs to the scope of protection of the invention.
It is the schematic flow sheet of cloud motion vector calculating method of the embodiment of the present invention based on pyramid light stream refering to Fig. 1.
The method of the embodiment of the present invention comprises the following steps:
S1:Two frame cloud layer images are continuously captured by the camera for vertically shooting ground.
S2:Detect multiple characteristic points of the first frame cloud layer image in two frame cloud layer images.
Wherein, characteristic point can be Harris angle points or marginal point.
S3:Two frame cloud layer images are compared using pyramid optical flow method, each characteristic point are estimated in two frame cloud layers
Position in image in the second frame cloud layer image.
Wherein, pyramid optical flow method is existing algorithm, and its substantially process is:First, one is set up to each frame cloud layer image
Individual gaussian pyramid, out to out image is in top, and original image is in the bottom;Then, estimate next since top
Frame position, as next layer of initial position, is searched for downwards along pyramid, repeats estimation action, until reaching golden word
The bottom of tower.
It should be noted that assumed condition should be followed using pyramid optical flow method, i.e.,:
(1)Brightness constancy, is exactly the change of same point over time, and its brightness will not change;
(2)Small motion, this must also is fulfilled for, and is exactly that the change of time will not cause the acute variation of position;
(3)Space is consistent, and neighbouring spot projection is to being also neighbor point on image in a scene, and neighbouring spot speed is consistent.
S4:Judge position of each characteristic point in the first frame cloud layer image relative to the position in the second frame cloud layer image
Put and whether change.
S5:If do not changed, corresponding characteristic point is filtered out, in the event of changing, then retains corresponding special
Levy a little.
Wherein, after the completion of location estimation of all characteristic points in the second frame cloud layer image, it is possible to which feature judged
The position of point changes, and which does not change.The characteristic point changed is retained, the characteristic point not changed
It is removed.
S6:The arrow for obtaining each characteristic point is calculated according to position of the characteristic point of each reservation in two frame cloud layer images
Amount.
Wherein, because the position of characteristic point changes, then according to the characteristic point of each reservation in two frame cloud layer figures
Pixel coordinate as in can calculate the vector for obtaining each characteristic point.
S7:According to characteristic point with a grain of salt Vector operation obtain characteristic point with a grain of salt resultant vector.
Wherein, the vector of characteristic point with a grain of salt will not be completely the same, but the overall motion of cloud layer can be embodied, because
This, according to characteristic point with a grain of salt Vector operation obtain characteristic point with a grain of salt resultant vector, it is possible to embody cloud fortune
Dynamic vector.
In the present embodiment, before step S2, this method also includes:Two frame cloud layer images are carried out using medium filtering
Smoothing processing.Medium filtering is a kind of nonlinear smoothing technology, is that can effectively suppress cloud layer based on the theoretical one kind of sequencing statistical
The nonlinear signal processing technology of picture noise, good using median filter method smooth effect, edge is clear, therefore, in
Value filtering is a kind of practicable method as smoothing processing to cloud layer image.The general principle of medium filtering is cloud layer image
The value of any in sequence is replaced with the Mesophyticum of each point value in a neighborhood of the point, makes the radar echo intensity value of surrounding closer
Actual value, so as to eliminate isolated noise spot.
Embodiments of the invention are the foregoing is only, are not intended to limit the scope of the invention, it is every to utilize this hair
Equivalent structure or equivalent flow conversion that bright specification and accompanying drawing content are made, or directly or indirectly it is used in other related skills
Art field, is included within the scope of the present invention.
Claims (2)
1. a kind of cloud motion vector calculating method based on pyramid light stream, it is characterised in that comprise the following steps:
S1:Two frame cloud layer images are continuously captured by the camera for vertically shooting ground;S2:Detect in the two frames cloud layer image
Multiple characteristic points of first frame cloud layer image;S3:The two frames cloud layer image is compared using pyramid optical flow method, estimated
Go out position of each characteristic point in the two frames cloud layer image in the second frame cloud layer image;S4:Judge each characteristic point
Whether the position in the first frame cloud layer image changes relative to the position in the second frame cloud layer image;
S5:If do not changed, corresponding characteristic point is filtered out, in the event of changing, then retains corresponding characteristic point;S6:
The vector for obtaining each characteristic point is calculated according to position of the characteristic point of each reservation in two frame cloud layer images;
S7:According to characteristic point with a grain of salt Vector operation obtain characteristic point with a grain of salt resultant vector.
2. according to the method described in claim 1, it is characterised in that before step S2, methods described also includes:
The two frames cloud layer image is smoothed using medium filtering.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710205760.XA CN106960445A (en) | 2017-03-31 | 2017-03-31 | A kind of cloud motion vector calculating method based on pyramid light stream |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710205760.XA CN106960445A (en) | 2017-03-31 | 2017-03-31 | A kind of cloud motion vector calculating method based on pyramid light stream |
Publications (1)
Publication Number | Publication Date |
---|---|
CN106960445A true CN106960445A (en) | 2017-07-18 |
Family
ID=59471070
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201710205760.XA Pending CN106960445A (en) | 2017-03-31 | 2017-03-31 | A kind of cloud motion vector calculating method based on pyramid light stream |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN106960445A (en) |
Cited By (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109146975A (en) * | 2018-08-22 | 2019-01-04 | 华北电力大学(保定) | A kind of sky image cloud cluster displacement vector calculation method |
CN109540142A (en) * | 2018-11-27 | 2019-03-29 | 达闼科技(北京)有限公司 | A kind of method, apparatus of robot localization navigation calculates equipment |
CN111220700A (en) * | 2019-12-09 | 2020-06-02 | 中北大学 | Ultrasonic cavitation bubble motion vector estimation method |
CN112712542A (en) * | 2020-12-25 | 2021-04-27 | 武汉大学 | Foundation cloud picture motion prediction method combining block matching and optical flow method |
CN112730884A (en) * | 2020-12-28 | 2021-04-30 | 同济大学建筑设计研究院(集团)有限公司 | Method and system for determining high-altitude wind speed by adopting imaging means |
CN115586798A (en) * | 2022-12-12 | 2023-01-10 | 广东电网有限责任公司湛江供电局 | Unmanned aerial vehicle anti-crash method and system |
-
2017
- 2017-03-31 CN CN201710205760.XA patent/CN106960445A/en active Pending
Cited By (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109146975A (en) * | 2018-08-22 | 2019-01-04 | 华北电力大学(保定) | A kind of sky image cloud cluster displacement vector calculation method |
CN109146975B (en) * | 2018-08-22 | 2022-02-01 | 华北电力大学(保定) | Sky image cloud cluster displacement vector calculation method |
CN109540142A (en) * | 2018-11-27 | 2019-03-29 | 达闼科技(北京)有限公司 | A kind of method, apparatus of robot localization navigation calculates equipment |
CN111220700A (en) * | 2019-12-09 | 2020-06-02 | 中北大学 | Ultrasonic cavitation bubble motion vector estimation method |
CN112712542A (en) * | 2020-12-25 | 2021-04-27 | 武汉大学 | Foundation cloud picture motion prediction method combining block matching and optical flow method |
CN112712542B (en) * | 2020-12-25 | 2024-02-02 | 武汉大学 | Foundation cloud picture motion prediction method combining block matching and optical flow method |
CN112730884A (en) * | 2020-12-28 | 2021-04-30 | 同济大学建筑设计研究院(集团)有限公司 | Method and system for determining high-altitude wind speed by adopting imaging means |
CN115586798A (en) * | 2022-12-12 | 2023-01-10 | 广东电网有限责任公司湛江供电局 | Unmanned aerial vehicle anti-crash method and system |
CN115586798B (en) * | 2022-12-12 | 2023-03-24 | 广东电网有限责任公司湛江供电局 | Unmanned aerial vehicle anti-crash method and system |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN106960445A (en) | A kind of cloud motion vector calculating method based on pyramid light stream | |
CN104318258B (en) | Time domain fuzzy and kalman filter-based lane detection method | |
CN103914843B (en) | The image partition method marked based on watershed algorithm and morphology | |
CN107369159B (en) | Threshold segmentation method based on multi-factor two-dimensional gray level histogram | |
CN102103753B (en) | Use method and the terminal of real time camera estimation detect and track Moving Objects | |
CN102252623B (en) | Measurement method for lead/ground wire icing thickness of transmission line based on video variation analysis | |
TWI420906B (en) | Tracking system and method for regions of interest and computer program product thereof | |
CN107203981B (en) | A kind of image defogging method based on fog concentration feature | |
CN108053419A (en) | Inhibited and the jamproof multiscale target tracking of prospect based on background | |
CN110517288A (en) | Real-time target detecting and tracking method based on panorama multichannel 4k video image | |
TW201120807A (en) | Apparatus and method for moving object detection | |
CN102346015A (en) | Method for measuring icing thickness of insulator of power transmission line based on video difference analysis | |
CN102620673A (en) | Tunnel deformation online monitoring system based on image analysis and application of system | |
CN107248174A (en) | A kind of method for tracking target based on TLD algorithms | |
CN107687819A (en) | A kind of optical losses sub-pixel extraction of quick high accuracy | |
CN109711256B (en) | Low-altitude complex background unmanned aerial vehicle target detection method | |
CN108776974A (en) | A kind of real-time modeling method method suitable for public transport scene | |
CN110309765B (en) | High-efficiency detection method for video moving target | |
CN103458261A (en) | Video scene variation detection method based on stereoscopic vision | |
CN109919026A (en) | A kind of unmanned surface vehicle local paths planning method | |
Li et al. | Road markings extraction based on threshold segmentation | |
CN101930606A (en) | Field depth extending method for image edge detection | |
CN111753693B (en) | Target detection method under static scene | |
CN114091620A (en) | Template matching detection method, computer equipment and storage medium | |
CN110473255A (en) | A kind of ship bollard localization method divided based on multi grid |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20170718 |
|
WD01 | Invention patent application deemed withdrawn after publication |