CN109885051A - A kind of ecological environment health quality appraisal procedure - Google Patents
A kind of ecological environment health quality appraisal procedure Download PDFInfo
- Publication number
- CN109885051A CN109885051A CN201910128295.3A CN201910128295A CN109885051A CN 109885051 A CN109885051 A CN 109885051A CN 201910128295 A CN201910128295 A CN 201910128295A CN 109885051 A CN109885051 A CN 109885051A
- Authority
- CN
- China
- Prior art keywords
- data
- ecological environment
- area
- map
- appraisal procedure
- 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
Landscapes
- Image Processing (AREA)
Abstract
The invention discloses a kind of ecological environment health quality appraisal procedure, include the following steps: the acquisition that area to be tested video data is carried out by unmanned plane；Pass through with the completing area to be tested map generalization of map generation module；The area to be tested map of monitoring objective and generation based on input generates monitoring point distribution map and robot ambulation path；The arrangement of monitoring device on each monitoring point is completed based on monitoring point distribution map and robot ambulation path using robot；The acquisition of each environmental parameters data is carried out based on monitoring device, and sends monitor terminal for supplemental characteristic through wireless communication module；After monitor terminal receives and completes the pretreatment of target data, the excavation of real-time weather data is carried out on each weather forecast base station by webcrawler module, and completes the assessment of current ecological environment based on the pretreated data of completion and its corresponding real-time weather data.The present invention substantially increases the accuracy of monitoring result, and easy to operate, and flexibility is high.
Description
Technical field
The present invention relates to ECOLOGICAL ENVIRONMENTAL MONITORING fields, and in particular to a kind of ecological environment health quality appraisal procedure.
Background technique
Ecological environment and human health have close relationship, currently, the quality of ecological environment has become mankind's emphasis pass
The focus of note.
It is more to the technique study of eco-environmental quality detection at present, but previous research method is both needed to carry out detection base
That stands builds, time-consuming and laborious, and the region of monitoring has significant limitation, while the data monitored are not where considering sensor
In position while the deployment scenarios such as vegetation, river, the influence of weather is not considered yet, reduces monitoring result to a certain extent
Accuracy.
Summary of the invention
To solve the above problems, substantially increasing prison the present invention provides a kind of ecological environment health quality appraisal procedure
The accuracy of result is surveyed, and easy to operate, flexibility is high.
To achieve the above object, the technical scheme adopted by the invention is as follows:
A kind of ecological environment health quality appraisal procedure, includes the following steps:
S1, the acquisition that area to be tested video data is carried out by unmanned plane；
S2, with the completing area to be tested map generalization by map generation module；
The area to be tested map of S3, the monitoring objective based on input and generation generate monitoring point distribution map and robot row
Walk path；
S4, corresponding on the monitoring point distribution map and robot ambulation path each monitoring point of completion supervise is based on using robot
The arrangement of measurement equipment；
S5, the acquisition that each environmental parameters data in the target ecological environment are carried out based on the monitoring device, and
Monitor terminal is sent by the supplemental characteristic through wireless communication module；
After S6, the monitor terminal receive and complete the pretreatment of target data, by webcrawler module in each weather
Forecast the excavation that real-time weather data are carried out on base station, and based on the pretreated data of completion and its corresponding real-time weather number
According to the assessment for completing current ecological environment.
Further, in the step S1, based on three-dimensional attitude sensor, GPS positioning chip, binocular vision nobody
Machine carry out video image acquisition, institute collected video image each section frame carry 3 d pose data.
Further, the step S2 specifically comprises the following steps:
S21, image is extracted as after framing interval is arranged in video；
S22, the adjustment that each picture deflection angle is realized based on 3 d pose data；
S23, using the image for most starting adjacent two frame resulting after Harris Corner Detection framing, extract key feature
Point；
S24, the Feature Points Matching that two images are realized by L-K optical flow method, and error hiding pair is eliminated with RANSAC algorithm
After obtaining homography matrix, the second width image is transformed to a width new images using perspective transform, is existed with the first width image co-registration
Together, two images splicing is completed, and so on, the image mosaic of entire video is completed, to obtain area to be tested map.
Further, it in the step S3, is primarily based on monitoring objective and calls corresponding monitoring point arrangement algorithm, then base
The label of monitoring point is completed on the area to be tested map using mark module in the monitoring point method for arranging of calling.
Further, in the step S3, firstly, being carried out respectively using bilateral filtering and piecewise linear transform algorithm to be checked
Survey the denoising and image enhancement pretreatment of area map；Image binaryzation processing is carried out using iteration self-adapting thresholding method,
Morphology area feature based on connected component removes the miscellaneous spot noise of small area, completes the identification of barrier position, and base
The identification of barrier shape and size is carried out in the length-width ratio of connected component boundary rectangle, completes crusing robot travel region
Calibration；It is then based on Robot Path Planning Algorithm and is based on resulting robot ambulation area data completion robot ambulation path
Planning.
Further, the monitoring device includes at least sensor, and the sensor includes sensor body, is included in biography
Rubber layer outside sensor ontology non-detection end and the pressure sensitive adhesive being arranged on rubber layer bottom surface.
Further, in the step S6, following processing mode is used for image data:
Area to be tested map partitioning is not first overlapped subregion, each sub-regions are extracted by depth convolution model
LBP feature, forming region histogram, then connect each region histogram to form Enhanced feature vector；
Be then based on the Enhanced feature vector using nearest neighbor classifier carry out assessment result output, thus realize to
The identification in vegetation, rubbish, river etc. in detection zone map.
Further, in the step S6, following processing mode is used for sensing data:
Firstly, the rough set Quick Attribution Reduction Algorithm based on Hadoop pre-processes sensing data, then will
It completes pretreated data and its corresponding real-time weather data input PCA-BP neural network model exports corresponding analysis
As a result.
Further, a data visualization analysis module is equipped in the monitor terminal, it is real by Tableau Desktop
The visual analyzing of existing data.
The invention has the following advantages:
1) arrangement and recycling that sensor is carried out by robot, while easy to use, flexibility is high；
2) the real-time weather data in region and the distribution situation in vegetation, river etc. will be monitored as assessment benchmark, can
More comprehensively to realize the accuracy for substantially increasing testing result while the understanding to ecological ring quality situation；
3) the rough set Quick Attribution Reduction Algorithm based on Hadoop carries out the pretreatment of data, improves the analysis of data
Efficiency is based on Tableau so as to which the mass data of numerous and complicated multiplicity is converted into the data available with target information
Desktop realizes the visual analyzing of data, so that the calculating for realizing plurality of target data obtains, greatly facilitates work
The use of personnel.
Detailed description of the invention
Fig. 1 is a kind of flow chart of ecological environment health quality appraisal procedure of the embodiment of the present invention.
Fig. 2 is the flow chart of step S2 in a kind of ecological environment health quality appraisal procedure of the embodiment of the present invention.
Specific embodiment
In order to which objects and advantages of the present invention are more clearly understood, the present invention is carried out with reference to embodiments further
It is described in detail.It should be appreciated that the specific embodiments described herein are merely illustrative of the present invention, it is not used to limit this hair
It is bright.
As shown in Figure 1, the embodiment of the invention provides a kind of ecological environment health quality appraisal procedures, including walk as follows
It is rapid:
S1, adopting for video image is carried out by the unmanned plane with three-dimensional attitude sensor, GPS positioning chip, binocular vision
Collection, institute collected video image each section frame carry 3 d pose data；Specifically, in the posture information of unmanned plane
Generated 3 d pose data are delivered to video image storage module automatically to realize different 3 d poses when changing
The differentiation of lower collected video data of data；
S2, with the completing area to be tested map generalization by map generation module；
The area to be tested map of S3, the monitoring objective based on input and generation generate monitoring point distribution map and robot row
Walk path；
S4, corresponding on the monitoring point distribution map and robot ambulation path each monitoring point of completion supervise is based on using robot
The arrangement of measurement equipment；
S5, the acquisition that each environmental parameters data in the target ecological environment are carried out based on the monitoring device, and
Monitor terminal is sent by the supplemental characteristic through wireless communication module；
After S6, the monitor terminal receive and complete the pretreatment of target data, by webcrawler module in each weather
Forecast the excavation that real-time weather data are carried out on base station, and based on the pretreated data of completion and its corresponding real-time weather number
According to the assessment for completing current ecological environment.
As shown in Fig. 2, the step S2 specifically comprises the following steps:
S21, image is extracted as after framing interval is arranged in video；
S22, the adjustment that each picture deflection angle is realized based on 3 d pose data；
S23, using the image for most starting adjacent two frame resulting after Harris Corner Detection framing, extract key feature
Point；
S24, the Feature Points Matching that two images are realized by L-K optical flow method, and error hiding pair is eliminated with RANSAC algorithm
After obtaining homography matrix, the second width image is transformed to a width new images using perspective transform, is existed with the first width image co-registration
Together, two images splicing is completed, and so on, the image mosaic of entire video is completed, to obtain area to be tested map.
In the present embodiment, in the step S3, it is primarily based on monitoring objective and calls corresponding monitoring point arrangement algorithm, then
Monitoring point method for arranging based on calling completes the label of monitoring point using mark module on the area to be tested map.
In the step S3, firstly, with carrying out area to be tested respectively using bilateral filtering and piecewise linear transform algorithm
The denoising of figure and image enhancement pretreatment；Image binaryzation processing is carried out using iteration self-adapting thresholding method, based on connection
The morphology area feature of component removes the miscellaneous spot noise of small area, completes the identification of barrier position, and based on connection point
The length-width ratio for measuring boundary rectangle carries out the identification of barrier shape and size, completes the calibration of crusing robot travel region；So
Complete the planning in robot ambulation path based on resulting robot ambulation area data based on Robot Path Planning Algorithm afterwards.
In the present embodiment, the monitoring device includes at least sensor, and the sensor includes sensor body, is included in
Rubber layer outside sensor body non-detection end and the pressure sensitive adhesive being arranged on rubber layer bottom surface.In use, there is supporter
When, such as building, number, bracket etc., it can directly paste on these supporters, facilitate installation and recycling, not support
When object, needs first to bury studdle through robot, then complete the arrangement of sensor, pass through ZigBee between each sensor node
Technology forms self-organizing network, and each sensor node transfers data to convergence by way of dynamic routing and multi-hop transmission
Node, aggregation node realize the very-long-range transmission of data by GPRS technology.
In the present embodiment, in the step S6, following processing mode is used for image data:
Area to be tested map partitioning is not first overlapped subregion, each sub-regions are extracted by depth convolution model
LBP feature, forming region histogram, then connect each region histogram to form Enhanced feature vector；
Be then based on the Enhanced feature vector using nearest neighbor classifier carry out assessment result output, thus realize to
The identification in vegetation, rubbish, river etc. in detection zone map.
In the present embodiment, in the step S6, following processing mode is used for sensing data:
Firstly, the rough set Quick Attribution Reduction Algorithm based on Hadoop pre-processes sensing data, then will
It completes pretreated data and its corresponding real-time weather data input PCA-BP neural network model exports corresponding analysis
As a result.
In the present embodiment, it is equipped with a data visualization analysis module in the monitor terminal, passes through Tableau Desktop
Realize the visual analyzing of data.
The above is only the preferred embodiment of the present invention, it is noted that those skilled in the art are come
It says, without departing from the principle of the present invention, can also make several improvements and retouch, these improvements and modifications also should be regarded as
Protection scope of the present invention.
Claims (9)
1. a kind of ecological environment health quality appraisal procedure, which comprises the steps of:
S1, the acquisition that area to be tested video data is carried out by unmanned plane；
S2, with the completing area to be tested map generalization by map generation module；
The area to be tested map of S3, the monitoring objective based on input and generation generate monitoring point distribution map and robot ambulation road
Diameter；
S4, it is based on corresponding to monitor on the monitoring point distribution map and robot ambulation path each monitoring point of completion using robot setting
Standby arrangement；
S5, the acquisition that each environmental parameters data in the target ecological environment are carried out based on the monitoring device, and through nothing
The supplemental characteristic is sent monitor terminal by line communication module；
After S6, the monitor terminal receive and complete the pretreatment of target data, by webcrawler module in each weather forecast
The excavation of real-time weather data is carried out on base station, and complete based on the pretreated data of completion and its corresponding real-time weather data
At the assessment of current ecological environment.
2. a kind of ecological environment health quality appraisal procedure as described in claim 1, it is characterised in that: in the step S1,
The acquisition that video image is carried out based on the unmanned plane with three-dimensional attitude sensor, GPS positioning chip, binocular vision, is collected
Video image the included 3 d pose data of each section frame.
3. a kind of ecological environment health quality appraisal procedure as described in claim 1, it is characterised in that: the step S2 is specific
Include the following steps:
S21, image is extracted as after framing interval is arranged in video；
S22, the adjustment that each picture deflection angle is realized based on 3 d pose data；
S23, using the image for most starting adjacent two frame resulting after Harris Corner Detection framing, extract key feature points；
S24, the Feature Points Matching that two images are realized by L-K optical flow method, and error hiding is eliminated to acquisition with RANSAC algorithm
After homography matrix, the second width image is transformed to a width new images using perspective transform, together with the first width image co-registration,
Two images splicing is completed, and so on, the image mosaic of entire video is completed, to obtain area to be tested map.
4. a kind of ecological environment health quality appraisal procedure as described in claim 1, it is characterised in that: in the step S3,
It is primarily based on monitoring objective and calls corresponding monitoring point arrangement algorithm, be then based on the monitoring point method for arranging of calling using label
Module completes the label of monitoring point on the area to be tested map.
5. a kind of ecological environment health quality appraisal procedure as described in claim 1, it is characterised in that: in the step S3,
Firstly, carrying out the denoising of area to be tested map respectively using bilateral filtering and piecewise linear transform algorithm and image enhancement is located in advance
Reason；Image binaryzation processing is carried out using iteration self-adapting thresholding method, the morphology area feature based on connected component is gone
Except the miscellaneous spot noise of small area, the identification of barrier position is completed, and is carried out based on the length-width ratio of connected component boundary rectangle
The calibration of crusing robot travel region is completed in the identification of barrier shape and size；It is then based on robot path planning's calculation
Method completes the planning in robot ambulation path based on resulting robot ambulation area data.
6. a kind of ecological environment health quality appraisal procedure as described in claim 1, it is characterised in that: the monitoring device is extremely
Less include sensor, the sensor include sensor body, include rubber layer outside sensor body non-detection end and
Pressure sensitive adhesive on rubber layer bottom surface is set.
7. a kind of ecological environment health quality appraisal procedure as described in claim 1, it is characterised in that: in the step S6,
Following processing mode is used for image data:
Area to be tested map partitioning is not first overlapped subregion, the LBP for extracting each sub-regions by depth convolution model is special
Sign, forming region histogram, then connect each region histogram to form Enhanced feature vector；
It is then based on the output that the Enhanced feature vector carries out assessment result using nearest neighbor classifier, to realize to be detected
The identification of vegetation, rubbish, river in area map.
8. a kind of ecological environment health quality appraisal procedure as described in claim 1, it is characterised in that: in the step S6,
Following processing mode is used for sensing data:
Firstly, the rough set Quick Attribution Reduction Algorithm based on Hadoop pre-processes sensing data, then will complete
Pretreated data and its corresponding real-time weather data input PCA-BP neural network model export corresponding analysis result.
9. a kind of ecological environment health quality appraisal procedure as described in claim 1, it is characterised in that: in the monitor terminal
Equipped with a data visualization analysis module, the visual analyzing of data is realized by Tableau Desktop.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910128295.3A CN109885051A (en) | 2019-02-21 | 2019-02-21 | A kind of ecological environment health quality appraisal procedure |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910128295.3A CN109885051A (en) | 2019-02-21 | 2019-02-21 | A kind of ecological environment health quality appraisal procedure |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109885051A true CN109885051A (en) | 2019-06-14 |
Family
ID=66928661
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910128295.3A Pending CN109885051A (en) | 2019-02-21 | 2019-02-21 | A kind of ecological environment health quality appraisal procedure |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109885051A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110470959A (en) * | 2019-08-27 | 2019-11-19 | 东北电力大学 | A kind of switch cabinet comprehensive on-line monitoring analysis platform |
| CN112506120A (en) * | 2020-12-02 | 2021-03-16 | 中国农业科学院农业信息研究所 | Wisdom fishery management system based on thing networking |
| CN113483820A (en) * | 2021-07-02 | 2021-10-08 | 中国路桥工程有限责任公司 | Highway along-line ecological environment health monitoring system based on 5G network |
Citations (18)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102621571A (en) * | 2012-03-08 | 2012-08-01 | 东南大学 | Method for distributing wireless sensor nodes for nuclear pollution detection |
| CN103177303A (en) * | 2013-04-18 | 2013-06-26 | 清华大学 | Data management system based on river ecological monitoring |
| CN103336790A (en) * | 2013-06-06 | 2013-10-02 | 湖州师范学院 | Hadoop-based fast neighborhood rough set attribute reduction method |
| CN106781370A (en) * | 2016-12-05 | 2017-05-31 | 西安科技大学 | Method is laid based on wireless communication propagation characteristic underground rescue robot communication node |
| CN107043000A (en) * | 2017-06-15 | 2017-08-15 | 西安科技大学 | A kind of belt conveyer safe and intelligent safeguards system based on machine vision |
| CN107176432A (en) * | 2017-06-15 | 2017-09-19 | 西安科技大学 | A kind of anchor pole foreign matter and belt tearing detecting system based on machine vision |
| CN107909508A (en) * | 2017-09-26 | 2018-04-13 | 国网辽宁省电力有限公司 | A kind of distribution transformer load abnormality alarming method |
| CN108009940A (en) * | 2017-11-10 | 2018-05-08 | 国网浙江省电力公司电力科学研究院 | Same period line loss exception analysis method and system based on Tableau |
| CN108092827A (en) * | 2018-01-23 | 2018-05-29 | 感知集团有限公司 | Ecological monitoring network and the means of communication based on LSN communication modules |
| CN108174464A (en) * | 2017-12-26 | 2018-06-15 | 江西师范大学 | A kind of forest ecological environment wireless sensor network monitoring system |
| CN108195933A (en) * | 2017-12-16 | 2018-06-22 | 商洛学院 | A kind of detecting system for detecting external wall mass defect |
| CN108319268A (en) * | 2018-02-08 | 2018-07-24 | 衢州职业技术学院 | A kind of robot navigation of view-based access control model moves into one's husband's household upon marriage method |
| CN108388862A (en) * | 2018-02-08 | 2018-08-10 | 西北农林科技大学 | Face identification method based on LBP features and nearest neighbor classifier |
| CN207999584U (en) * | 2018-03-23 | 2018-10-23 | 北京城市排水集团有限责任公司 | A kind of monitoring fiber deployment device being combined with existing pipeline rehabilitation |
| CN108921787A (en) * | 2018-06-11 | 2018-11-30 | 东北电力大学 | Photovoltaic module image split-joint method based on infrared video |
| CN108960141A (en) * | 2018-07-04 | 2018-12-07 | 国家新闻出版广电总局广播科学研究院 | Pedestrian's recognition methods again based on enhanced depth convolutional neural networks |
| CN109283937A (en) * | 2018-09-18 | 2019-01-29 | 广东省智能制造研究所 | A kind of plant protection based on unmanned plane sprays the method and system of operation |
| CN109299078A (en) * | 2018-11-28 | 2019-02-01 | 哈尔滨工业大学 | A kind of sports center's evacuation database building method based on crowd behaviour |
-
2019
- 2019-02-21 CN CN201910128295.3A patent/CN109885051A/en active Pending
Patent Citations (18)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102621571A (en) * | 2012-03-08 | 2012-08-01 | 东南大学 | Method for distributing wireless sensor nodes for nuclear pollution detection |
| CN103177303A (en) * | 2013-04-18 | 2013-06-26 | 清华大学 | Data management system based on river ecological monitoring |
| CN103336790A (en) * | 2013-06-06 | 2013-10-02 | 湖州师范学院 | Hadoop-based fast neighborhood rough set attribute reduction method |
| CN106781370A (en) * | 2016-12-05 | 2017-05-31 | 西安科技大学 | Method is laid based on wireless communication propagation characteristic underground rescue robot communication node |
| CN107043000A (en) * | 2017-06-15 | 2017-08-15 | 西安科技大学 | A kind of belt conveyer safe and intelligent safeguards system based on machine vision |
| CN107176432A (en) * | 2017-06-15 | 2017-09-19 | 西安科技大学 | A kind of anchor pole foreign matter and belt tearing detecting system based on machine vision |
| CN107909508A (en) * | 2017-09-26 | 2018-04-13 | 国网辽宁省电力有限公司 | A kind of distribution transformer load abnormality alarming method |
| CN108009940A (en) * | 2017-11-10 | 2018-05-08 | 国网浙江省电力公司电力科学研究院 | Same period line loss exception analysis method and system based on Tableau |
| CN108195933A (en) * | 2017-12-16 | 2018-06-22 | 商洛学院 | A kind of detecting system for detecting external wall mass defect |
| CN108174464A (en) * | 2017-12-26 | 2018-06-15 | 江西师范大学 | A kind of forest ecological environment wireless sensor network monitoring system |
| CN108092827A (en) * | 2018-01-23 | 2018-05-29 | 感知集团有限公司 | Ecological monitoring network and the means of communication based on LSN communication modules |
| CN108319268A (en) * | 2018-02-08 | 2018-07-24 | 衢州职业技术学院 | A kind of robot navigation of view-based access control model moves into one's husband's household upon marriage method |
| CN108388862A (en) * | 2018-02-08 | 2018-08-10 | 西北农林科技大学 | Face identification method based on LBP features and nearest neighbor classifier |
| CN207999584U (en) * | 2018-03-23 | 2018-10-23 | 北京城市排水集团有限责任公司 | A kind of monitoring fiber deployment device being combined with existing pipeline rehabilitation |
| CN108921787A (en) * | 2018-06-11 | 2018-11-30 | 东北电力大学 | Photovoltaic module image split-joint method based on infrared video |
| CN108960141A (en) * | 2018-07-04 | 2018-12-07 | 国家新闻出版广电总局广播科学研究院 | Pedestrian's recognition methods again based on enhanced depth convolutional neural networks |
| CN109283937A (en) * | 2018-09-18 | 2019-01-29 | 广东省智能制造研究所 | A kind of plant protection based on unmanned plane sprays the method and system of operation |
| CN109299078A (en) * | 2018-11-28 | 2019-02-01 | 哈尔滨工业大学 | A kind of sports center's evacuation database building method based on crowd behaviour |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110470959A (en) * | 2019-08-27 | 2019-11-19 | 东北电力大学 | A kind of switch cabinet comprehensive on-line monitoring analysis platform |
| CN112506120A (en) * | 2020-12-02 | 2021-03-16 | 中国农业科学院农业信息研究所 | Wisdom fishery management system based on thing networking |
| CN113483820A (en) * | 2021-07-02 | 2021-10-08 | 中国路桥工程有限责任公司 | Highway along-line ecological environment health monitoring system based on 5G network |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106356757B (en) | A kind of power circuit unmanned plane method for inspecting based on human-eye visual characteristic | |
| Fan et al. | Rethinking road surface 3-d reconstruction and pothole detection: From perspective transformation to disparity map segmentation | |
| CN109886192A (en) | A kind of ecological environment intelligent monitor system | |
| CN109885051A (en) | A kind of ecological environment health quality appraisal procedure | |
| CN103679674B (en) | Method and system for splicing images of unmanned aircrafts in real time | |
| CN107491071B (en) | Intelligent multi-robot cooperative mapping system and method thereof | |
| CN105426837B (en) | Mobile network's vision haze detection system | |
| CN104517095B (en) | A kind of number of people dividing method based on depth image | |
| Kawano et al. | Road marking blur detection with drive recorder | |
| CN106485751B (en) | Unmanned aerial vehicle photographic imaging and data processing method and system applied to foundation pile detection | |
| CN105510787A (en) | Portable ultrasonic, infrared and ultraviolet detector based on image synthesis technology | |
| CN105486751A (en) | Equipment defect comprehensive detection system | |
| Fang et al. | A point cloud-vision hybrid approach for 3D location tracking of mobile construction assets | |
| Li et al. | A robot vision navigation method using deep learning in edge computing environment | |
| CN205507005U (en) | Portable supersound, infrared, ultraviolet detector | |
| CN111811502B (en) | Motion carrier multi-source information fusion navigation method and system | |
| CN102682435B (en) | Multi-focus image edge detection method based on space relative altitude information | |
| Jiang et al. | Foreign object recognition technology for port transportation channel based on automatic image recognition | |
| Shokri et al. | Utility poles extraction from mobile LiDAR data in urban area based on density information | |
| Wang et al. | 3D reconstruction and segmentation system for pavement potholes based on improved structure-from-motion (SFM) and deep learning | |
| CN107231553A (en) | Corner location acquisition methods and device | |
| CN106682668A (en) | Power transmission line geological disaster monitoring method using unmanned aerial vehicle to mark images | |
| CN103903269B (en) | The description method and system of ball machine monitor video | |
| CN115409691A (en) | Bimodal learning slope risk detection method integrating laser ranging and monitoring image | |
| CN113532424B (en) | Integrated equipment for acquiring multidimensional information and cooperative measurement 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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190614 |
|
| RJ01 | Rejection of invention patent application after publication |