CN109934110A - A kind of river squatter building house recognition methods nearby - Google Patents
A kind of river squatter building house recognition methods nearby Download PDFInfo
- Publication number
- CN109934110A CN109934110A CN201910107890.9A CN201910107890A CN109934110A CN 109934110 A CN109934110 A CN 109934110A CN 201910107890 A CN201910107890 A CN 201910107890A CN 109934110 A CN109934110 A CN 109934110A
- Authority
- CN
- China
- Prior art keywords
- house
- outline
- area
- river
- recognition methods
- 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.)
- Granted
Links
Landscapes
- Image Analysis (AREA)
Abstract
The present invention relates to squatter building house recognition methods near a kind of river, comprising the following steps: S1: several river orthographies that unmanned plane is shot are spliced into a width panoramic picture；S2: dwelling feature training is carried out to initial semantic segmentation algorithm by the panoramic picture, obtains outline of house identification model；S3: extracting the outline of house pixel in the panoramic picture by the outline of house identification model, and by outline of house pixel vector；S4: squatter building mark in house is carried out to the outline of house pixel after vector quantization.River of the present invention squatter building house recognition methods nearby works instead of the traditional artificial profile mark for carrying out house and vector quantization, improves the efficiency of outline of house extraction.
Description
Technical field
The present invention relates to building squatter buildings to identify field, more particularly to squatter building house recognition methods near a kind of river.
Background technique
To ensure that river course flood is unimpeded, according to relevant regulations, construction house is not allow in certain distance near the river
, it is therefore desirable to the building near river is checked, wherein the identification and area extraction right and wrong of the buildings such as house
Often important step.Currently, the identification and area extraction method to river squatter building house are usually to pass through unmanned plane along river
Center carries out the high angle shot of specific range to river, by high angle shot image co-registration at a complete river orthography, then will just penetrate
Image is imported by manually carrying out the profile mark in house near river in professional software, while vector is melted into SHP file, most
Overlapping area extraction is carried out to vector quantization house by establishing river buffer area afterwards, while the house of squatter building is identified.By
Very long in the river for needing to shoot, the building of river both sides is again very intensive, therefore the profile by manually carrying out house
Mark and vector quantization work expend time and manpower very much.There is statistics, the mistake of the artificial profile mark and vector quantization for carrying out house
The entire floor space of Cheng Yuezhan extract and 40% time of squatter building identification procedure and 80% human resources.As it can be seen that traditional people
The profile that work carries out house identifies and the process efficiency of vector quantization is too low, is unable to satisfy project duration demand.
Summary of the invention
Based on this, the object of the present invention is to provide squatter building house recognition methods near a kind of river, have and improve room
The advantages of room profile mark and vector quantization working efficiency.
A kind of river squatter building house recognition methods nearby, comprising the following steps:
S1: several river orthographies that unmanned plane is shot are spliced into a width panoramic picture；
S2: dwelling feature training is carried out to initial semantic segmentation algorithm by the panoramic picture, outline of house is obtained and knows
Other model；
S3: extracting the outline of house pixel in the panoramic picture by the outline of house identification model, and by house
Contour pixel vector quantization；
S4: squatter building mark in house is carried out to the outline of house pixel after vector quantization.
River of the present invention squatter building house recognition methods nearby is identified instead of the traditional artificial profile for carrying out house
And vector quantization work, improve the efficiency of outline of house extraction.
Further, in the step S2 the following steps are included:
S201: building backbone feature extractor extracts dwelling feature, obtains characteristic information figure；
S202: the port number that convolution algorithm reduces characteristic information figure is carried out to the characteristic information figure, obtains fisrt feature
Figure；
S203: building spatial pyramid pond carries out pond to the fisrt feature figure, and carries out bilinear interpolation deconvolution
Obtain second feature figure；
S204: the fisrt feature figure and second feature figure are subjected to Fusion Features, obtain feature atlas, and to the spy
Sign atlas does convolution and bilinear interpolation de-convolution operation, obtains prediction image；
S205: according to preset mark image, the prediction image and mark image is subjected to cross entropy calculating and damaged
Vector；
S206: optimization is iterated to the outline of house identification model using the loss amount, obtains the house of optimization
Outline identification model.
Further, further comprising the steps of after step S206 in the step S2: S207: the room that will optimize
Room outline identification model encapsulation is at outline of house extracting tool.
Further, further comprising the steps of in step s3: the outline of house identification model is extracted into outline of house
Characteristic pattern after dyad quantization exports SHP file.
Further, Morphological scale-space also is done to the prediction image before outline of house extracts in the step S3.
Further, the Morphological scale-space includes expansion, burn into open and close operation.
Further, in the step S4 the following steps are included:
S401: the outline of house area in the prediction image is calculated；
S402: it builds buffer area and calculates buffer area area in the river two sides in the prediction image；
S403: the buffer area area and the outline of house area are subjected to overlapping calculating, obtain the outline of house
With the intersection area area of buffer area；
S404: the intersection area of the outline of house and buffer area is identified as squatter building floor area.
Further, specifically includes the following steps: preset area threshold values, extracts outline of house point set in the step S401
And contour area is calculated, the contour area is compared with preset area threshold values, contour area is less than the default face
The region removal of product threshold values；Default rectangular degree threshold values carries out rectangular degree calculating to each outline of house, will be less than the default square
The profile of shape bottom valve value removes；The outline of house point set is uniformly diluted, by the outline of house point set vector after dilution
Change.
The present invention also provides a kind of computer-readable storage medias, store computer program thereon, the computer journey
The step of squatter building house recognition methods nearby of river described in any one as above is realized when sequence is executed by processor.
The present invention also provides a kind of computer equipment, including reservoir, processor and it is stored in the reservoir
And the computer program that can be executed by the processor, the processor are realized as above any one when executing the computer program
Near river described in the step of the recognition methods of squatter building house.
In order to better understand and implement, the invention will now be described in detail with reference to the accompanying drawings.
Detailed description of the invention
Fig. 1 is the flow chart of river of the present invention squatter building house recognition methods nearby；
Fig. 2 is the flow chart of step 2 of the present invention；
Fig. 3 is outline of house of the present invention extraction and vector quantization schematic diagram；
Fig. 4 is the functional block diagram of outline of house extracting tool of the present invention.
Specific embodiment
In the description of the present invention, it is to be understood that, term " center ", " longitudinal direction ", " transverse direction ", "upper", "lower",
The orientation or positional relationship of the instructions such as "front", "rear", "left", "right", "vertical", "horizontal", "top", "bottom", "inner", "outside" is
It is based on the orientation or positional relationship shown in the drawings, is merely for convenience of description of the present invention and simplification of the description, rather than instruction or dark
Show that signified device or element must have a particular orientation, be constructed and operated in a specific orientation, therefore should not be understood as pair
Limitation of the invention.In the description of the present invention, unless otherwise indicated, the meaning of " plurality " is two or more.
Please refer to Fig. 1-3, Fig. 1 is the flow chart of river of the present invention squatter building house recognition methods nearby；Fig. 2 is
The flow chart of step 2 of the present invention；Fig. 3 is outline of house of the present invention extraction and vector quantization schematic diagram.
Equipment used in the squatter building house recognition methods nearby of this river includes unmanned plane, is equipped on taking the photograph on unmanned plane
Camera and the image processing arrangement for being set to ground station；Be equipped in the image processing arrangement Arcgis software,
Tensorflow learning framework and Open CV image procossing library.
In the present embodiment, control unmanned plane flies along river center；Video camera carries out high angle shot to river and obtains several rivers
Orthograph picture, and the orthograph picture is sent to progress house squatter building identification in the professional software of the image processing arrangement.
The river nearby the recognition methods of squatter building house the following steps are included:
S1: several river orthographies that unmanned plane is shot are spliced into a width panoramic picture；
S2: dwelling feature training is carried out to initial semantic segmentation algorithm by the panoramic picture, outline of house is obtained and knows
Other model；
S3: extracting the outline of house pixel in the panoramic picture by the outline of house identification model, and by house
Contour pixel vector quantization；
S4: squatter building mark in house is carried out to the outline of house pixel after vector quantization.
In the present embodiment, the initial semantic segmentation algorithm uses DeepLabv3+ algorithm, and in other embodiments, this is first
Beginning semantic segmentation algorithm can also use other algorithms, such as mask-RCNN, FCN and U-Net scheduling algorithm.
In the present embodiment, in step s 2 specifically includes the following steps:
S201: building backbone feature extractor extracts dwelling feature, obtains characteristic information figure；
S202: the port number that convolution algorithm reduces characteristic information figure is carried out to the characteristic information figure, obtains fisrt feature
Figure；
S203: building spatial pyramid pond carries out pond to the fisrt feature figure, and carries out bilinear interpolation deconvolution
Obtain second feature figure；
S204: the fisrt feature figure and second feature figure are subjected to Fusion Features, obtain feature atlas, and to the spy
Sign atlas does convolution and bilinear interpolation de-convolution operation, obtains prediction image；
S205: according to preset mark image, the prediction image and mark image is subjected to cross entropy calculating and damaged
Vector；
S206: optimization is iterated to the outline of house identification model using the loss amount, obtains the house of optimization
Outline identification model；
S207: the outline of house identification model optimized is packaged into outline of house extracting tool.
Wherein the extracted dwelling feature of backbone feature extractor includes: profile, shape, color and Texture eigenvalue.
It constructs spatial pyramid pond and pond is carried out to characteristic pattern, solve the problems, such as that input picture must be fixed-size, from
And the image aspect ratio of input and size can be made any.
It is further comprising the steps of in step s3: after the outline of house identification model is extracted outline of house dyad quantization
Characteristic pattern export SHP file.
The prediction image also do at morphology by Open CV before outline of house extracts in the step S3
Reason makes outline of house be more nearly actual profile to distinguish the outline of house to link together.
And outline of house pixel point set is obtained in the laggard having sexual intercourse room contours extract of Morphological scale-space, and by outline of house pixel
Vector quantization.
In addition, user can also choose whether vector according to demand turns to SHP file, SHP text is turned to when not needing vector
When part, outline of house image can also directly be extracted and save as JPG file.
Specifically, the Morphological scale-space includes expansion, burn into open and close operation.
1, it expands: being exactly the operation for seeking local maximum, carrying out original image in judge templet region with maximum value is on earth
It is placed in 1 and is also placed in 0, to for bianry image, go to each upper position on traversal image with the template of specific structure, if
It is 1 that, which there is a point in template specific structure position, then the position that specific structure is corresponded on image is all 1.
2, corrode: effect of the corrosion in mathematical morphological operation is the boundary point for eliminating object.In Digital Image Processing
In, for determining structural element, the point less than structural element can be eliminated by erosion operation.A meanwhile if target area
Contain tiny coupling part in domain, then can be split to region by honest and sincere processing.
The relationship wherein corroded and expanded are as follows: set target image such as A, structural element S is indicated to carry out A corruption with A-S
Operation is lost, is indicated to carry out expansion budget to A with A+S.
It is described corrosion and expansion application be boundary extraction: the extraction on boundary be by target image carry out corrosion or
The difference of expansion process, comparison result image and original image is realized；The corrosion treatment of the extraction and application image of inner boundary obtains
To a contraction of original image, then result and target image progress XOR operation will be shunk；The extraction of outer boundary is to target image
Expansion process is carried out, then carries out XOR operation using expansion results and former target image.
3, opening operation and closed operation:
Opening operation: A zero S=(A-S)+S (reflation is first corroded to target image)
Closed operation: A ● S=(A+S)-S (target image is first expanded and is corroded again)
The opening operation of image is usually used to carry out denoising to target image, meanwhile, the opening operation of image can choose
Retain the part for meeting structure primary colors geometric properties in target image to property, and portion damaged for filtering out opposed configuration element
Point.
The closed operation of image be usually used to the region separated to target image be attached and to fine gap in image into
Row is filled up, and by properly selecting structural element, the closed operation of image can enable the geometry of image filled up result and have a bit
Feature suitably can be such that image becomes more fully apparent image progress closed operation coherent sometimes, while can be to avoid original image
Middle lines overstriking.
In the present embodiment, in the step S4 specifically includes the following steps:
S401: the outline of house area in the prediction image is calculated；
S402: it builds buffer area and calculates buffer area area in the river two sides in the prediction image；
S403: the buffer area area and the outline of house area are subjected to overlapping calculating, obtain the outline of house
With the intersection area area of buffer area；
S404: the intersection area of the outline of house and buffer area is identified as squatter building floor area.
Specifically includes the following steps: preset area threshold values, extracts outline of house point set and calculate in the step S401
Contour area compares the contour area with preset area threshold values, and contour area is less than the preset area threshold values
Region removal；Default rectangular degree threshold values carries out rectangular degree calculating to each outline of house, will be less than the default rectangular degree threshold values
Profile removal；The outline of house point set is uniformly diluted, by the outline of house point set vector quantization after dilution.
Specifically, it is preset with minimized profile area-limit；The area for calculating each outline of house simultaneously, by the area
It compared with minimized profile area-limit, removes and disregards if being less than minimum area threshold values, obtain outline of house area A
contour；Orthography is imported into Arcgis software, builds the buffer area of specific range in river two sides, and calculate
The area A buffer of buffer area, by the river buffer area area A buffer and the outline of house area A contour
Carry out overlapping calculating: A IoU=Abuffer ∩ Acontour；Obtain transfer area A Io U, that is, obtain the outline of house with
The intersection area of the outline of house and buffer area is set as squatter building floor area, and identified by the intersection area of buffer area.
In the present embodiment, buffer area is the six meters of buffer areas extended from river to two sides or ten meters of buffer areas and other distances
Buffer area.
In addition, the figure shown in computer can be generally divided into two major classes: polar plot and bitmap.Polar plot uses straight line
Figure is described with curve, the element of these figures is some points, line, rectangle, polygon, circle and camber line etc., they are all
Acquisition is calculated by mathematical formulae.Such as one the vector graphics drawn of width be actually that outline border profile formed by line segment, by outline border
Color and outline border closed color determine the color that flower is shown.It is obtained since vector graphics can be calculated by formula,
So vector graphics file volume is typically small.Vector image has many good qualities: firstly, vector image is by simple geometric graphic element
Composition indicates compact, and shared memory space is small；Secondly, vector image is easy to be edited, vector image is edited
When, such as rotated, stretched, translating the parameter information for only needing to modify corresponding geometric graphic element when operation；Third uses vector
The object of expression is easy to amplify or compress, and will not reduce its display quality in a computer, the scaling of vector image
The characteristics such as sharp of corner are able to maintain, are not in that Fuzzy Influence shows quality.Therefore, by orthography in the present embodiment
After outline of house feature extraction, carrying out vector quantization is important step therein.
Referring to Fig. 4, Fig. 4 is the functional block diagram of outline of house extracting tool of the present invention.The outline of house mentions
It takes and the function of vector quantization tool includes image management, image operation, image is shown, outline of house extracts, parameter setting and text
Part export.Specifically, image management may include that individual image imports, multiple images import and predicts that the functions such as Image preservation are grasped
Make；Image operation may include image-zooming, the up and down feature operations such as image selection, image rotation；Image, which is shown, can wrap
Include the feature operations such as whole image load and the load of fractional prediction image；Outline of house extraction may include deep learning module tune
With feature operations such as, super large Image Segmentation and image joints；Parameter setting may include model parameter setting and cutting image ginseng
The feature operations such as number setting；File export may include the feature operations such as the export of contour vectorization file and prediction address generation.
The squatter building house recognition methods nearby of this river, collects river orthograph picture by unmanned plane first, then pass through
Arcgis software is by several river orthographs of acquisition as anastomosing and splicing is at the complete full-view image of a width；Then splicing is good complete
Scape image imports outline of house and extracts in software, carries out outline of house extraction according to user demand and Vector contour is shp
File；The shp file and orthography are finally imported into arcgis software, and establishes buffer area and carries out overlapping area calculating, and
Identify violation house.This method can greatly improve the working efficiency of outline of house extraction, can save outline of house extraction
And the time of vector quantization；Manpower is saved simultaneously, only needs to have people's operating software；And the deep learning algorithm is in entirety
The extraction accuracy of image is up to 93.53%.
The present invention also provides a kind of computer-readable storage medias, store computer program thereon, the computer program
The step of river squatter building house recognition methods nearby as described in above-mentioned any one is realized when being executed by processor.
It wherein includes storage medium (the including but not limited to disk of program code that the present invention, which can be used in one or more,
Memory, CD-ROM, optical memory etc.) on the form of computer program product implemented.Computer-readable storage media packet
Permanent and non-permanent, removable and non-removable media is included, can be accomplished by any method or technique information storage.Letter
Breath can be computer readable instructions, data structure, the module of program or other data.The example packet of the storage medium of computer
Include but be not limited to: phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM),
Other kinds of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory
(EEPROM), flash memory or other memory techniques, read-only disc read only memory (CD-ROM) (CD-ROM), digital versatile disc
(DVD) or other optical storage, magnetic cassettes, tape magnetic disk storage or other magnetic storage devices or any other non-biography
Defeated medium, can be used for storage can be accessed by a computing device information.
The present invention also provides a kind of computer equipment, including reservoir, processor and it is stored in the reservoir simultaneously
The computer program that can be executed by the processor, the processor are realized when executing the computer program as above-mentioned any one
Near river described in the step of the recognition methods of squatter building house.
The embodiments described above only express several embodiments of the present invention, and the description thereof is more specific and detailed, but simultaneously
It cannot therefore be construed as limiting the scope of the patent.It should be pointed out that coming for those of ordinary skill in the art
It says, without departing from the inventive concept of the premise, various modifications and improvements can be made, these belong to protection of the invention
Range.
Claims (10)
1. a kind of squatter building house recognition methods nearby of river, it is characterised in that: the following steps are included:
S1: several river orthographies that unmanned plane is shot are spliced into a width panoramic picture；
S2: dwelling feature training is carried out to initial semantic segmentation algorithm by the panoramic picture, outline of house is obtained and identifies mould
Type；
S3: extracting the outline of house pixel in the panoramic picture by the outline of house identification model, and by outline of house
Pixel vector；
S4: squatter building mark in house is carried out to the outline of house pixel after vector quantization.
2. river according to claim 1 squatter building house recognition methods nearby, it is characterised in that: include in the step S2
Following steps:
S201: building backbone feature extractor extracts dwelling feature, obtains characteristic information figure；
S202: the port number that convolution algorithm reduces characteristic information figure is carried out to the characteristic information figure, obtains fisrt feature figure；
S203: building spatial pyramid pond carries out pond to the fisrt feature figure, and carries out bilinear interpolation deconvolution acquisition
Second feature figure；
S204: the fisrt feature figure and second feature figure are subjected to Fusion Features, obtain feature atlas, and to the characteristic pattern
Collection does convolution and bilinear interpolation de-convolution operation, obtains prediction image；
S205: according to preset mark image, the prediction image and mark image is subjected to cross entropy and calculate acquisition loss amount；
S206: optimization is iterated to the outline of house identification model using the loss amount, obtains the outline of house of optimization
Identification model.
3. river according to claim 2 squatter building house recognition methods nearby, it is characterised in that: in the step S2,
Further comprising the steps of after step S206: S207: the outline of house identification model that will optimize is packaged into outline of house extraction
Tool.
4. river according to claim 1 squatter building house recognition methods nearby, it is characterised in that: further include in step s3
Following steps: the characteristic pattern that the outline of house identification model is extracted after outline of house dyad quantization is exported into SHP file.
5. river according to claim 1 squatter building house recognition methods nearby, it is characterised in that: also exist in the step S3
Outline of house does Morphological scale-space to the prediction image before extracting.
6. river according to claim 5 squatter building house recognition methods nearby, it is characterised in that: the Morphological scale-space packet
Include expansion, burn into open and close operation.
7. river according to claim 1 squatter building house recognition methods nearby, it is characterised in that: include in the step S4
Following steps:
S401: the outline of house area in the prediction image is calculated；
S402: it builds buffer area and calculates buffer area area in the river two sides in the prediction image；
S403: the buffer area area and the outline of house area are subjected to overlapping calculating, the outline of house is obtained and delays
Rush the intersection area area in area；
S404: the intersection area of the outline of house and buffer area is identified as squatter building floor area.
8. river according to claim 7 squatter building house recognition methods nearby, it is characterised in that: have in the step S401
Body extracts outline of house point set and simultaneously calculates contour area the following steps are included: preset area threshold values, by the contour area with
Preset area threshold values compares, and the region that contour area is less than the preset area threshold values is removed；Default rectangular degree threshold values, it is right
Each outline of house carries out rectangular degree calculating, and the profile for being less than the default rectangular degree threshold values is removed；To the outline of house
Point set is uniformly diluted, by the outline of house point set vector quantization after dilution.
9. a kind of computer-readable storage media, stores computer program thereon, which is characterized in that the computer program is located
Reason device realizes the step of river as claimed in any of claims 1 to 8 in one of claims squatter building house recognition methods nearby when executing.
10. a kind of computer equipment, which is characterized in that including reservoir, processor and be stored in the reservoir and can
The computer program executed by the processor, the processor realize such as claim 1 to 8 when executing the computer program
Any one of described in river nearby the recognition methods of squatter building house the step of.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910107890.9A CN109934110B (en) | 2019-02-02 | 2019-02-02 | Method for identifying illegal buildings near river channel |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910107890.9A CN109934110B (en) | 2019-02-02 | 2019-02-02 | Method for identifying illegal buildings near river channel |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109934110A true CN109934110A (en) | 2019-06-25 |
| CN109934110B CN109934110B (en) | 2021-01-12 |
Family
ID=66985575
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910107890.9A Active CN109934110B (en) | 2019-02-02 | 2019-02-02 | Method for identifying illegal buildings near river channel |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109934110B (en) |
Cited By (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111062361A (en) * | 2019-12-27 | 2020-04-24 | 中水北方勘测设计研究有限责任公司 | Method and device for monitoring and analyzing sand production on river and lake shoreline |
| CN111104879A (en) * | 2019-12-09 | 2020-05-05 | 贝壳技术有限公司 | Method and device for identifying house functions, readable storage medium and electronic equipment |
| CN111382696A (en) * | 2020-03-06 | 2020-07-07 | 北京百度网讯科技有限公司 | Method and apparatus for detecting boundary points of object |
| CN111382695A (en) * | 2020-03-06 | 2020-07-07 | 北京百度网讯科技有限公司 | Method and apparatus for detecting boundary points of object |
| CN111523391A (en) * | 2020-03-26 | 2020-08-11 | 上海刻羽信息科技有限公司 | Building identification method, system, electronic device and readable storage medium |
| CN111652892A (en) * | 2020-05-02 | 2020-09-11 | 王磊 | Remote sensing image building vector extraction and optimization method based on deep learning |
| CN112651338A (en) * | 2020-12-26 | 2021-04-13 | 广东电网有限责任公司电力科学研究院 | Method and device for distinguishing hidden danger of illegal construction of power transmission line |
| CN113536836A (en) * | 2020-04-15 | 2021-10-22 | 宁波弘泰水利信息科技有限公司 | Method for monitoring river and lake water area encroachment based on unmanned aerial vehicle remote sensing technology |
| CN113724117A (en) * | 2020-12-28 | 2021-11-30 | 京东城市(北京)数字科技有限公司 | Model training method and device for house abnormal use recognition |
| CN114549569A (en) * | 2022-03-01 | 2022-05-27 | 中国电建集团中南勘测设计研究院有限公司 | House contour extraction method based on two-dimensional ortho-image |
| CN115100531A (en) * | 2022-07-26 | 2022-09-23 | 复旦大学 | Unmanned aerial vehicle vision-based illegal construction inspection and measurement method and system |
| CN117237705A (en) * | 2023-08-29 | 2023-12-15 | 广州粤建三和软件股份有限公司 | Potential safety hazard management system for self-built house |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP2418606A2 (en) * | 2010-08-13 | 2012-02-15 | Pantech Co., Ltd. | Apparatus and method for recognizing objects using filter information |
| CN102930540A (en) * | 2012-10-26 | 2013-02-13 | 中国地质大学（武汉） | Method and system for detecting contour of urban building |
| CN105608691A (en) * | 2015-12-17 | 2016-05-25 | 武汉大学 | High-resolution SAR image individual building extraction method |
| CN105929845A (en) * | 2016-05-18 | 2016-09-07 | 中国计量大学 | Unmanned aerial vehicle network-based river channel cruise system and cruise method |
| CN106934156A (en) * | 2017-03-13 | 2017-07-07 | 中国水利水电科学研究院 | It is a kind of to build dangerous spot recognition methods along river course |
| CN108764039A (en) * | 2018-04-24 | 2018-11-06 | 中国科学院遥感与数字地球研究所 | Building extracting method, medium and the computing device of neural network, remote sensing image |
| CN109242291A (en) * | 2018-08-28 | 2019-01-18 | 天津大学 | River and lake basin water environment wisdom management method |
-
2019
- 2019-02-02 CN CN201910107890.9A patent/CN109934110B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP2418606A2 (en) * | 2010-08-13 | 2012-02-15 | Pantech Co., Ltd. | Apparatus and method for recognizing objects using filter information |
| CN102930540A (en) * | 2012-10-26 | 2013-02-13 | 中国地质大学（武汉） | Method and system for detecting contour of urban building |
| CN105608691A (en) * | 2015-12-17 | 2016-05-25 | 武汉大学 | High-resolution SAR image individual building extraction method |
| CN105929845A (en) * | 2016-05-18 | 2016-09-07 | 中国计量大学 | Unmanned aerial vehicle network-based river channel cruise system and cruise method |
| CN106934156A (en) * | 2017-03-13 | 2017-07-07 | 中国水利水电科学研究院 | It is a kind of to build dangerous spot recognition methods along river course |
| CN108764039A (en) * | 2018-04-24 | 2018-11-06 | 中国科学院遥感与数字地球研究所 | Building extracting method, medium and the computing device of neural network, remote sensing image |
| CN109242291A (en) * | 2018-08-28 | 2019-01-18 | 天津大学 | River and lake basin water environment wisdom management method |
Non-Patent Citations (2)
| Title |
|---|
| YU WANG等: "Research on Illegal Building Detection Based on the Change Discovery and Spatial Morphological Characteristics of Image", 《2018 2ND INTERNATIONAL CONFERENCE ON APPLIED MATHEMATICS, MODELING AND SIMULATION》 * |
| 鲁佳隽: "无人机河道巡检系统设计与实现", 《中国优秀硕士学位论文全文数据库工程科技Ⅱ辑》 * |
Cited By (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111104879A (en) * | 2019-12-09 | 2020-05-05 | 贝壳技术有限公司 | Method and device for identifying house functions, readable storage medium and electronic equipment |
| CN111062361A (en) * | 2019-12-27 | 2020-04-24 | 中水北方勘测设计研究有限责任公司 | Method and device for monitoring and analyzing sand production on river and lake shoreline |
| CN111382696A (en) * | 2020-03-06 | 2020-07-07 | 北京百度网讯科技有限公司 | Method and apparatus for detecting boundary points of object |
| CN111382695A (en) * | 2020-03-06 | 2020-07-07 | 北京百度网讯科技有限公司 | Method and apparatus for detecting boundary points of object |
| CN111523391A (en) * | 2020-03-26 | 2020-08-11 | 上海刻羽信息科技有限公司 | Building identification method, system, electronic device and readable storage medium |
| CN113536836A (en) * | 2020-04-15 | 2021-10-22 | 宁波弘泰水利信息科技有限公司 | Method for monitoring river and lake water area encroachment based on unmanned aerial vehicle remote sensing technology |
| CN111652892A (en) * | 2020-05-02 | 2020-09-11 | 王磊 | Remote sensing image building vector extraction and optimization method based on deep learning |
| CN112651338A (en) * | 2020-12-26 | 2021-04-13 | 广东电网有限责任公司电力科学研究院 | Method and device for distinguishing hidden danger of illegal construction of power transmission line |
| CN112651338B (en) * | 2020-12-26 | 2022-02-15 | 广东电网有限责任公司电力科学研究院 | Method and device for distinguishing hidden danger of illegal construction of power transmission line |
| CN113724117A (en) * | 2020-12-28 | 2021-11-30 | 京东城市(北京)数字科技有限公司 | Model training method and device for house abnormal use recognition |
| CN114549569A (en) * | 2022-03-01 | 2022-05-27 | 中国电建集团中南勘测设计研究院有限公司 | House contour extraction method based on two-dimensional ortho-image |
| CN114549569B (en) * | 2022-03-01 | 2024-04-09 | 中国电建集团中南勘测设计研究院有限公司 | House contour extraction method based on two-dimensional orthographic image |
| CN115100531A (en) * | 2022-07-26 | 2022-09-23 | 复旦大学 | Unmanned aerial vehicle vision-based illegal construction inspection and measurement method and system |
| CN117237705A (en) * | 2023-08-29 | 2023-12-15 | 广州粤建三和软件股份有限公司 | Potential safety hazard management system for self-built house |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109934110B (en) | 2021-01-12 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109934110A (en) | A kind of river squatter building house recognition methods nearby | |
| CN107767413A (en) | A kind of image depth estimation method based on convolutional neural networks | |
| US20240169674A1 (en) | Indoor scene virtual roaming method based on reflection decomposition | |
| CN104954780B (en) | A kind of DIBR virtual image restorative procedure suitable for the conversion of high definition 2D/3D | |
| US20190057532A1 (en) | Realistic augmentation of images and videos with graphics | |
| CN106815808A (en) | A kind of image split-joint method of utilization piecemeal computing | |
| CN107610131A (en) | A kind of image cropping method and image cropping device | |
| WO2008067363A2 (en) | Soft edge smoothness prior and application on alpha channel super resolution | |
| CN112184585B (en) | Image completion method and system based on semantic edge fusion | |
| US20190221034A1 (en) | Computer handling of object silhouettes | |
| CN113409332B (en) | Building plane segmentation method based on three-dimensional point cloud | |
| CN105761314B (en) | A kind of Model Simplification Method kept based on notable color attribute feature | |
| CN116385672A (en) | Construction method of three-dimensional terrain scene model data product | |
| CN112132466A (en) | Route planning method, device and equipment based on three-dimensional modeling and storage medium | |
| CN109064533A (en) | A kind of 3D loaming method and system | |
| CN115937461A (en) | Multi-source fusion model construction and texture generation method, device, medium and equipment | |
| WO2024125434A1 (en) | Regional-consistency-based building principal angle correction method | |
| CN114283266A (en) | Three-dimensional model adjusting method and device, storage medium and equipment | |
| CN116091709B (en) | Three-dimensional reconstruction method and device for building, electronic equipment and storage medium | |
| CN117011658A (en) | Image processing method, apparatus, device, storage medium, and computer program product | |
| CN115311418B (en) | Multi-detail-level tree model single reconstruction method and device | |
| CN115375847B (en) | Material recovery method, three-dimensional model generation method and model training method | |
| CN109087250B (en) | Image splicing method based on regular boundary constraint | |
| CN115620137A (en) | Method and system for generating greening area | |
| CN115546455A (en) | Three-dimensional building model monomer method, device and storage medium |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |