CN113920026A - Method for removing noise of regional landslide deformation detection result - Google Patents
Method for removing noise of regional landslide deformation detection result Download PDFInfo
- Publication number
- CN113920026A CN113920026A CN202111167943.XA CN202111167943A CN113920026A CN 113920026 A CN113920026 A CN 113920026A CN 202111167943 A CN202111167943 A CN 202111167943A CN 113920026 A CN113920026 A CN 113920026A
- Authority
- CN
- China
- Prior art keywords
- image
- deformation
- deformation detection
- images
- detection result
- 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
- 238000001514 detection method Methods 0.000 title claims abstract description 75
- 238000000034 method Methods 0.000 title claims abstract description 29
- 238000007619 statistical method Methods 0.000 claims abstract description 10
- 238000012937 correction Methods 0.000 claims abstract description 9
- 239000013598 vector Substances 0.000 claims description 36
- 230000003287 optical effect Effects 0.000 claims description 13
- 238000004364 calculation method Methods 0.000 claims description 10
- 238000006073 displacement reaction Methods 0.000 claims description 10
- 230000015572 biosynthetic process Effects 0.000 claims description 6
- 238000003786 synthesis reaction Methods 0.000 claims description 6
- 238000001308 synthesis method Methods 0.000 claims description 2
- 238000012544 monitoring process Methods 0.000 abstract description 3
- 238000005516 engineering process Methods 0.000 description 3
- 230000002159 abnormal effect Effects 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000008030 elimination Effects 0.000 description 1
- 238000003379 elimination reaction Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 230000036544 posture Effects 0.000 description 1
- 239000002243 precursor Substances 0.000 description 1
- 230000002265 prevention Effects 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 230000000717 retained effect Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000009897 systematic effect Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/70—Denoising; Smoothing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T3/00—Geometric image transformations in the plane of the image
- G06T3/60—Rotation of whole images or parts thereof
-
- 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
- G06T2207/10—Image acquisition modality
- G06T2207/10032—Satellite or aerial image; Remote sensing
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Image Processing (AREA)
Abstract
The invention discloses a method for removing noise of a regional landslide deformation detection result. Based on the characteristic that the strips in the deformation detection result have directionality, the strips are rotated to the vertical direction according to the strip inclination angle, the noise removing method for line-by-line statistical analysis and correction is provided, a stable area does not need to be selected manually, and strip noise can be automatically corrected in a large area scale. The method can realize automatic deformation detection in a large-scale area, can quickly evaluate the sub-pixel level surface deformation, calculates the surface deformation quantity and deformation direction, and provides a basic technical method for geological disaster monitoring and early warning, emergency disposal and the like.
Description
Technical Field
The invention relates to the fields of remote sensing technology, emergency management and disaster prevention and reduction, in particular to a method for removing noise of a regional landslide deformation detection result.
Background
Mountain disasters such as landslide pose serious threats to mountain areas around the world, and slope deformation is an important precursor to the imminent occurrence of such mountain disasters. With the increase of population size and economic activity, it is very important to detect the potential slope deformation of mountainous areas. By using the deformation detection technology and the optical remote sensing image data, the deformation detection of the slope of the mountain area in a large area range and at the sub-pixel level can be carried out. Under the influence of shooting postures of the satellite sensor and the like, overall systematic deviation of deformation detection results often occurs in local areas, and strip noise appears in detection results in the whole image results, so that the precision and the efficiency of landslide deformation detection are directly influenced, and the application of the deformation detection technology in a large-range area is limited. In order to eliminate deformation detection deviation in local areas, previous researches are mostly carried out in non-landslide areas, stable areas are manually selected to evaluate the system deviation, and the strategy is difficult to be used for deviation elimination in large areas.
Disclosure of Invention
In order to overcome the problems in the prior art, the invention provides a method for removing noise of a regional landslide deformation detection result. The method can realize automatic deformation detection in a large-scale area, can quickly evaluate the sub-pixel level surface deformation, calculates the surface deformation quantity and deformation direction, and provides a basic technical method for geological disaster monitoring and early warning, emergency disposal and the like.
The purpose of the invention is realized by the following technical scheme:
a method for removing noise of a regional landslide deformation detection result, the method comprising the following steps:
step 1: selecting a plurality of Image pairs for optical remote sensing before and after the detection time pointpair(ii) a Image-based Image pair Image detection method using deformation detectionpairPerforming preliminary deformation detection calculation to obtain a preliminary deformation detection result Image of the detection area1Image (Image)1The deformation direction vector of the east-west direction is represented by EW, the deformation direction vector of the south-north direction is represented by NS, and the signal-to-noise ratio is represented by SNR;
step 2: removing Image based on cloud mask data of optical remote sensing Image1Obtaining the Image of the deformation detection result of the pixels of the middle cloud coverage area2；
And step 3: acquiring Image2Rotating the Image at an inclination angle alpha of the middle strip to enable the Image strip to be vertically crossed with the horizontal direction, and acquiring the rotated Imagerotate1；
And 4, step 4: image after rotationrotate1The vector images of the EW and NS directions are preprocessed, pixels with the value of 0 are removed, the pixels are assigned to be null values, then the pixel values of the EW and NS images corresponding to the pixel positions with the signal-to-noise ratio value of less than 0.9 in the SNR images are assigned to be null values respectively, and preprocessed deformation detection result Image images are obtainedrotate2；
And 5: for Imagerotate2The EW and NS direction vector images are respectively subjected to column-by-column statistical analysis and correction, and the specific calculation method is as follows: 1) obtaining the standard deviation std column by columncolAnd meancolAnd 2) counting that the pixel value in each column is greater than meancol-stdcolAnd is less than meancol+stdcolMean of the range Meancol3) the value of each pel of the column minus Meancol(ii) a After the line-by-line statistical analysis and correction, the Image is obtainedrotate3；
Step 6: imagerotate3The EW and NS direction vectors and the SNR Image are rotated according to the reverse direction-alpha angle to obtain an Image3Wherein, the EW and NS direction vector images are both subjected to stripe noise removal;
and 7: image-based Image3Vector synthesis is carried out on the EW and NS direction vector images to obtain Image4Thus, the deformation detection result image based on the optical image with the stripe noise removed is obtained, and the deformation detection result image comprises two images of deformation displacement and deformation direction.
Further optimization, selecting a plurality of images of optical remote sensing before and after the detection time point in the step 1 for ImagepairThe specific operation is as follows: selecting optical remote sensing images before and after the detection time point, selecting remote sensing images with the julian day not more than 5 days and the cloud cover rate lower than 10%, and forming a plurality of Image pairspair。
Further, the Image in step 32The method for acquiring the inclination angle (alpha) of the middle strip comprises the following steps: selecting an obvious strip from the image, recording image coordinates of a plurality of (5) points along the strip, fitting a straight line y, wherein y is the image ordinate direction, x is the image abscissa direction, k is the slope of the fitting straight line, and m is the intercept of the fitting straight line, and calculating the inclination angle (alpha) of the strip according to the straight line slope k by using a calculation formula alpha, arctan (k) x 180/pi.
Further, in step 3, image coordinates of at least 5 points are recorded along the strip and a straight line y ═ kx + m is fitted.
Further, the synthesis method in step 7 comprises: vector synthesis of vector images in two directions of EW and NS is carried out pixel by pixel according to the following formula, a deformation detection result image is obtained, and the deformation displacement and the deformation direction of each pixel position are respectively obtained:
in the formula: distance is deformation displacement, direction is deformation direction, and EW and NS respectively represent pixels of vector images in EW and NS directions.
The invention principle of the invention is as follows:
considering that the stripes of the result image have directivity, the invention provides a column-by-column statistical matching method from the viewpoint of the directivity of stripe noise.
Based on the characteristic that the strips in the deformation detection result have directionality, the invention firstly rotates the strips to the vertical direction according to the strip inclination angle, provides a noise removal method for line-by-line statistical analysis and correction, does not need to manually select a stable area, and can realize the automatic correction of the strip noise in a large area scale.
The column-by-column statistical analysis and correction method realizes the column-by-column standardization of the rotating image and improves the accuracy of global noise removal of the deformation detection image.
According to the method, the deformation detection preliminary result is preprocessed by removing clouds, eliminating pixel values with zero values and signal-to-noise ratio values less than 0.9, abnormal values influencing large-area statistical analysis are deleted, and useful information of the landslide deformation detection result can be retained to the greatest extent.
The invention has the advantages and beneficial effects that:
on the regional scale, a stable region does not need to be selected for estimating deviation; after null values and abnormal values are eliminated, statistical analysis operation is carried out on the image, and stripe noise can be automatically corrected globally; useful information of the landslide deformation detection result can be reserved to the greatest extent.
The method can realize automatic deformation detection in a large-scale area, can quickly evaluate the sub-pixel level surface deformation, calculates the surface deformation quantity and deformation direction, and provides a basic technical method for geological disaster monitoring and early warning, emergency disposal and the like.
Drawings
The invention is further illustrated by the following figures and examples.
FIG. 1 is an Image of example 11A deformation direction vector image example of the north-south direction (NS);
FIG. 2 is a schematic diagram of a method for calculating a tilt angle of a strip in example 1;
FIG. 3 shows the Image after rotation in example 1rotateNorth-south (NS) morphed direction vector image examples in an image;
FIG. 4 is an Image of the deformation detection result in example 1rotate3A medium north-south direction (NS) morphed direction vector image example;
FIG. 5 is the Image after reverse rotation in example 13A medium north-south direction (NS) morphed direction vector image example;
FIG. 6 is a histogram comparison chart of the total deformation detection result image NS before and after removing noise in example 1;
FIG. 7 shows the results of detection of regional distortion Image in example 14The image includes (a) a strain displacement amount image and (b) a strain direction image.
Detailed Description
Example 1:
in order to better understand the technical solution of the present invention, the following description further describes an embodiment of the present invention with reference to the accompanying drawings.
The embodiment of the invention provides a method for removing noise of a regional landslide deformation detection result, which comprises the following steps:
step 1: in the example, a Sentinel-2 satellite remote sensing image is selected as an example, the Sentinel-2 time sequence remote sensing image data before and after the detection time point are obtained, and based on the Sentinel-2 time sequence remote sensing image data, julian days in each year are selected to be similar (the front and back do not exceed 5 days), and the cloud cover rate is low (the cloud cover rate is low)<10%) of remote sensing images to form a plurality of Image pairspair(ii) a Then, The selected Image pair Image is subjected to a distortion detection method, such as The Cossi-Corr method (The Co-registration of optical Sensed Images and Correlation, COSI-Corr), based on The selected Image pair ImagepairPerforming preliminary deformation detection calculation to obtain a preliminary deformation detection result Image of the detection area1Deformation direction vectors in the east-west direction and the south-north direction and signal-to-noise ratios are respectively expressed by EW, NS and SNR;
step 2: removing the Image of the preliminary deformation detection result based on the cloud mask data of the Sentinel-2 Image1Obtaining the Image of the deformation detection result of the pixels of the middle cloud coverage area2；
And step 3: obtaining an Image of a preliminary deformation detection result2Rotating the Image by the inclination angle (alpha) of the middle strip to enable the Image strip to be vertically intersected with the horizontal direction, and acquiring the rotated primary deformation detection result Imagerotate；
The method for acquiring the inclination angle (alpha) of the image strip comprises the following steps: selecting an obvious strip from the image, recording image coordinates of a plurality of (5) points along the strip, fitting a straight line y, wherein y is the image ordinate direction, x is the image abscissa direction, k is the slope of the fitting straight line, and m is the intercept of the fitting straight line, and calculating the inclination angle (alpha) of the strip according to the straight line slope k by using a calculation formula alpha, arctan (k) x 180/pi.
The inclination angle calculation scheme of the image band is shown in table 1, fig. 2, and fig. 3, for example:
TABLE 1 coordinate information of 5 points in an image strip
| x coordinate | y coordinate |
| 2576 | 965 |
| 2468 | 1410 |
| 2350 | 1888 |
| 2268 | 2242 |
| 2185 | 2580 |
And 4, step 4: rotated preliminary deformation detection result Imagerotate1The vector images of the EW and NS directions are preprocessed, pixels with the value of 0 are removed, the pixels are assigned to be null values, pixels with the signal-to-noise ratio value of less than 0.9 in the SNR Image are taken as reference, the values of the positions of the corresponding pixels in the EW and NS images are removed, the values are assigned to be null values respectively, and preprocessed deformation detection result Image images are obtainedrotate2；
And 5: preprocessed detection result Imagerotate2Respectively carrying out column-by-column statistics on EW and NS direction vector images in the imageAnalyzing and correcting, wherein the specific calculation method comprises the following steps: 1) obtaining the standard deviation std column by columncolAnd meancolAnd 2) counting that the pixel value in each column is greater than (mean)col-stdcol) And is less than (mean)col+stdcol) Mean of the range Meancol3) the value of each pel of the column minus Meancol. After the line-by-line statistical analysis and correction, obtaining a deformation detection result Imagerotate3(ii) a As shown in fig. 4;
step 6: image of deformation detection resultrotate3The EW and NS direction vectors and the SNR Image are rotated according to the reverse direction (-alpha), and the Image is obtained3(FIG. 5) where both EW and NS direction vector images have been strip noise removed; comparing histograms (fig. 6) of the images of the deformation detection results before and after noise removal can find that the image data before noise removal is relatively discrete, the image data after noise removal is more concentrated and conforms to normal distribution, which indicates that the image quality is improved after noise removal.
Step 7 is based on the EW and NS direction vector Image subjected to cloud cover removal, banding removal and noise processingrotate3Performing vector synthesis to obtain Image4Thus, the deformation detection result image based on the optical image with the stripe noise removed is obtained, and the deformation detection result image comprises two images of deformation displacement and deformation direction. Vector synthesis of vector images in two directions of EW and NS is carried out pixel by pixel according to the following formula, a deformation detection result image is obtained, and the deformation displacement and the deformation direction of each pixel position are respectively obtained:
in the formula: distance is deformation displacement, direction is deformation direction, and EW and NS respectively represent pixels of vector images in EW and NS directions. The results are shown in FIG. 7.
Finally, it should be noted that the above only illustrates the technical solution of the present invention, but not limited thereto, and although the present invention has been described in detail with reference to the preferred arrangement, it will be understood by those skilled in the art that modifications or equivalent substitutions may be made thereto without departing from the spirit and scope of the technical solution of the present invention.
Claims (5)
1. A method for removing noise of a regional landslide deformation detection result is characterized by comprising the following steps:
step 1: selecting a plurality of Image pairs for optical remote sensing before and after the detection time pointpair(ii) a Image-based Image pair Image detection method using deformation detectionpairPerforming preliminary deformation detection calculation to obtain a preliminary deformation detection result Image of the detection area1Image (Image)1The deformation direction vector of the east-west direction is represented by EW, the deformation direction vector of the south-north direction is represented by NS, and the signal-to-noise ratio is represented by SNR;
step 2: removing Image based on cloud mask data of optical remote sensing Image1Obtaining the Image of the deformation detection result of the pixels of the middle cloud coverage area2；
And step 3: acquiring Image2Rotating the Image at an inclination angle alpha of the middle strip to enable the Image strip to be vertically crossed with the horizontal direction, and acquiring the rotated Imagerotate1；
And 4, step 4: image after rotationrotate1The vector images of the EW and NS directions are preprocessed, pixels with the value of 0 are removed, the pixels are assigned to be null values, then the pixel values of the EW and NS images corresponding to the pixel positions with the signal-to-noise ratio value of less than 0.9 in the SNR images are assigned to be null values respectively, and preprocessed deformation detection result Image images are obtainedrotate2；
And 5: for Imagerotate2The EW and NS direction vector images are respectively subjected to column-by-column statistical analysis and correction, and the specific calculation method is as follows: 1) obtainingStandard deviation std column by columncolAnd meancolAnd 2) counting that the pixel value in each column is greater than meancol-stdcolAnd is less than meancol+stdcolMean of the range Meancol3) the value of each pel of the column minus Meancol(ii) a After the line-by-line statistical analysis and correction, the Image is obtainedrotate3；
Step 6: imagerotate3The EW and NS direction vectors and the SNR Image are rotated according to the reverse direction-alpha angle to obtain an Image3Wherein, the EW and NS direction vector images are both subjected to stripe noise removal;
and 7: image-based Image3Vector synthesis is carried out on the EW and NS direction vector images to obtain Image4Thus, the deformation detection result image based on the optical image with the stripe noise removed is obtained, and the deformation detection result image comprises two images of deformation displacement and deformation direction.
2. The method for removing noise of regional landslide deformation detection results according to claim 1, wherein in step 1, selecting optical remote sensing images before and after detection time point to ImagepairThe specific operation is as follows: selecting optical remote sensing images before and after the detection time point, selecting remote sensing images with the julian day not more than 5 days and the cloud cover rate lower than 10%, and forming a plurality of Image pairspair。
3. The method according to claim 1, wherein the Image in step 3 is used for removing noise of regional landslide deformation detection results2The method for acquiring the inclination angle (alpha) of the middle strip comprises the following steps: selecting an obvious strip from the image, recording image coordinates of a plurality of (5) points along the strip, fitting a straight line y, wherein y is the image ordinate direction, x is the image abscissa direction, k is the slope of the fitting straight line, and m is the intercept of the fitting straight line, and calculating the inclination angle (alpha) of the strip according to the straight line slope k by using a calculation formula alpha, arctan (k) x 180/pi.
4. The method for removing noise of regional landslide deformation detection results according to claim 3, wherein in step 3, image coordinates of at least 5 points are recorded along a strip and a straight line y ═ kx + m is fitted.
5. The method for removing noise of regional landslide deformation detection results according to claim 1, wherein the synthesis method of step 7 is as follows: vector synthesis of vector images in two directions of EW and NS is carried out pixel by pixel according to the following formula, a deformation detection result image is obtained, and the deformation displacement and the deformation direction of each pixel position are respectively obtained:
in the formula: distance is deformation displacement, direction is deformation direction, and EW and NS respectively represent pixels of vector images in EW and NS directions.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111167943.XA CN113920026A (en) | 2021-09-30 | 2021-09-30 | Method for removing noise of regional landslide deformation detection result |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111167943.XA CN113920026A (en) | 2021-09-30 | 2021-09-30 | Method for removing noise of regional landslide deformation detection result |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113920026A true CN113920026A (en) | 2022-01-11 |
Family
ID=79238120
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111167943.XA Pending CN113920026A (en) | 2021-09-30 | 2021-09-30 | Method for removing noise of regional landslide deformation detection result |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113920026A (en) |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102279971A (en) * | 2011-04-06 | 2011-12-14 | 中国人民解放军理工大学气象学院 | Variational method-based method for reducing stripe noise of moderate-resolution imaging spectroradiometer |
| CN102750683A (en) * | 2012-06-18 | 2012-10-24 | 常州大学 | Filtering method for sea surface stripe noise and sea surface stripe cloud in moderate resolution imaging spectroradiometer (MODIS) remote sensing image |
| CN108681993A (en) * | 2018-05-10 | 2018-10-19 | 中国国土资源航空物探遥感中心 | Based on normalized domestic high-resolution remote sensing image Strip noise removal method |
| CN109613513A (en) * | 2018-12-20 | 2019-04-12 | 长安大学 | A kind of potential landslide automatic identifying method of optical remote sensing for taking InSAR deformation into account |
-
2021
- 2021-09-30 CN CN202111167943.XA patent/CN113920026A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102279971A (en) * | 2011-04-06 | 2011-12-14 | 中国人民解放军理工大学气象学院 | Variational method-based method for reducing stripe noise of moderate-resolution imaging spectroradiometer |
| CN102750683A (en) * | 2012-06-18 | 2012-10-24 | 常州大学 | Filtering method for sea surface stripe noise and sea surface stripe cloud in moderate resolution imaging spectroradiometer (MODIS) remote sensing image |
| CN108681993A (en) * | 2018-05-10 | 2018-10-19 | 中国国土资源航空物探遥感中心 | Based on normalized domestic high-resolution remote sensing image Strip noise removal method |
| CN109613513A (en) * | 2018-12-20 | 2019-04-12 | 长安大学 | A kind of potential landslide automatic identifying method of optical remote sensing for taking InSAR deformation into account |
Non-Patent Citations (2)
| Title |
|---|
| WENWEN QI ET AL: "Detecting Chamoli landslide precursors in the southern Himalayas using remote sensing data", 《RECENT LANDSLIDES》 * |
| 秦雁 等: "分段线性动态矩匹配条带去除", 《中国图象图形学报》 * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109146794B (en) | A kind of light field image rotation error bearing calibration | |
| CN107563964B (en) | Rapid splicing method for large-area-array sub-meter-level night scene remote sensing images | |
| CN110807809B (en) | Light-weight monocular vision positioning method based on point-line characteristics and depth filter | |
| CN109934788B (en) | Remote sensing image missing data restoration method based on standard remote sensing image | |
| CN112419380B (en) | Cloud mask-based high-precision registration method for stationary orbit satellite sequence images | |
| CN113298810B (en) | Road line detection method combining image enhancement and depth convolution neural network | |
| CN108919319B (en) | Method and system for positioning island reef satellite image without ground control point | |
| CN110414308B (en) | Target identification method for dynamic foreign matters on power transmission line | |
| CN112348775B (en) | Vehicle-mounted looking-around-based pavement pit detection system and method | |
| CN113160053B (en) | Pose information-based underwater video image restoration and splicing method | |
| CN108364279B (en) | Method for determining pointing deviation of stationary orbit remote sensing satellite | |
| Dolloff et al. | An assessment of WorldView-1 positional accuracy based on fifty contiguous stereo pairs of imagery | |
| CN113920026A (en) | Method for removing noise of regional landslide deformation detection result | |
| CN113139994B (en) | High-resolution optical remote sensing satellite image building height monitoring method based on angular points | |
| CN111640141B (en) | Low-speed target positioning and tracking method based on thermal imaging | |
| CN111862005A (en) | Method and system for accurately positioning tropical cyclone center by using synthetic radar image | |
| CN116091494B (en) | Method for measuring distance of hidden danger of external damage of power transmission machinery | |
| CN116863357A (en) | Unmanned aerial vehicle remote sensing dyke image calibration and intelligent segmentation change detection method | |
| CN114397476B (en) | Flow velocity effectiveness identification and correction method for frequency domain space-time image velocity measurement | |
| CN113936009B (en) | Cloud shadow removing method, device and equipment for meteorological satellite flood monitoring | |
| CN115937267A (en) | Target track tracking method based on multi-frame video | |
| CN115063394A (en) | Depth estimation method integrating image correction and parallax estimation | |
| Qin et al. | A coarse elevation map-based registration method for super-resolution of three-line scanner images | |
| CN111583298B (en) | Short-time cloud picture tracking method based on optical flow method | |
| CN111860161B (en) | Target shielding detection method |
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 |