CN113421299B - Water depth measuring system and method based on water level gauge and camera - Google Patents
Water depth measuring system and method based on water level gauge and camera Download PDFInfo
- Publication number
- CN113421299B CN113421299B CN202110712712.6A CN202110712712A CN113421299B CN 113421299 B CN113421299 B CN 113421299B CN 202110712712 A CN202110712712 A CN 202110712712A CN 113421299 B CN113421299 B CN 113421299B
- Authority
- CN
- China
- Prior art keywords
- water
- water level
- level gauge
- camera
- depth
- 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.)
- Active
Links
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 title claims abstract description 199
- 238000000034 method Methods 0.000 title claims abstract description 16
- 238000010586 diagram Methods 0.000 claims abstract description 33
- 238000012545 processing Methods 0.000 claims abstract description 23
- 230000005540 biological transmission Effects 0.000 claims abstract description 8
- 230000011218 segmentation Effects 0.000 claims description 18
- 238000011176 pooling Methods 0.000 claims description 8
- 230000009286 beneficial effect Effects 0.000 claims description 5
- 238000004364 calculation method Methods 0.000 claims description 4
- 238000005259 measurement Methods 0.000 claims description 3
- 238000013473 artificial intelligence Methods 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 230000006978 adaptation Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 238000011835 investigation Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/70—Determining position or orientation of objects or cameras
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/11—Region-based segmentation
Landscapes
- Engineering & Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Measurement Of Levels Of Liquids Or Fluent Solid Materials (AREA)
- Image Processing (AREA)
Abstract
The invention discloses a water depth measuring system and a water depth measuring method based on a water level gauge and a camera, wherein the system comprises the following modules: a wireless digital fluviograph; a water depth value transmission module; a camera; an image transmission module; a data receiving module; and a background processing module. The invention can measure the regional flooding depth in the camera picture and generate a regional flooding isodepth line schematic diagram. The invention can be used for evaluating urban waterlogging, and provides basis for government decision-making departments to make policies such as urban drainage, rescue and relief work, traffic control and the like. The urban area flooding condition measured by the method can also be provided for the public, and references are provided for public travel, risk avoidance and the like.
Description
Technical Field
The invention belongs to the technical field of computer vision, and particularly relates to a water depth measuring system and method based on a water level gauge and a camera.
Background
In recent years, with the development of artificial intelligence technology, various industries have gradually combined with artificial intelligence technology to realize intelligence, and smart cities have also been developed. The method has the advantages that the method is suitable for urban waterlogging, early warning and disposal of urban waterlogging are also frequently encountered problems in many cities in municipal administration, loss of lives and properties of citizens can be possibly caused if the urban waterlogging cannot be found and early warned in time, and on-site investigation by municipal personnel is very time-consuming and labor-consuming, so that the flooding depth needs to be estimated intelligently through a water level meter and a camera, and information such as the position, the depth and the like of the flooding area in the cities is summarized, so that the method has practical significance for rescuing disaster relief or early warning for citizens.
The invention can measure the regional flooding depth in the camera picture and generate a regional flooding isodepth line schematic diagram. The invention can be used for evaluating urban waterlogging, and provides basis for government decision-making departments to make policies such as urban drainage, rescue and relief work, traffic control and the like. The urban area flooding condition measured by the method can also be provided for the public, and references are provided for public travel, risk avoidance and the like.
Disclosure of Invention
The invention aims to provide an intelligent water flooding depth measuring system and method based on a water level gauge and a camera.
In order to achieve the technical purpose, the invention adopts the following technical scheme:
a water depth measurement system based on a water level gauge and a camera, comprising the following modules:
the water level gauge is used for measuring the water depth;
the water depth value transmission module is used for transmitting the measured water depth value of the water level gauge to the receiving module;
the camera is used for acquiring an area image of the water level gauge area;
the image transmission module is used for transmitting the area image data of the water level gauge area acquired by the camera to the receiving module;
the data receiving module is used for transmitting the received data to the background processing module;
and the background processing module is used for processing the water level gauge and camera data.
In order to optimize the technical scheme, the specific measures adopted further comprise:
the camera acquires images in a snap shooting mode.
The mounting height and angle of the camera cover the corresponding water level gauge area.
The camera is used for calibrating the covered water level gauge position.
The water level gauge uses a wireless digital water level gauge.
The water level gauge is used for transmitting water depth readings at fixed time and controlling whether the camera captures images or not;
the water level gauge is provided with a water depth threshold, when the water level gauge reading is smaller than the threshold, the camera does not do any work, when the water level gauge reading is larger than the water depth threshold, the camera captures images, and the current water level gauge reading and the camera capture images are transmitted to the background processing module through the receiving module.
The background processing module comprises a water surface area segmentation model and is used for detecting the water surface area in the image and updating the depth isodepth line graph according to the current reading of the water level gauge.
The water surface area segmentation model adopts an improved UNet model to segment a flooded area in a snap shot image of a camera, and specifically comprises the following steps:
the improved UNet model adopts zero padding in a convolution layer, the size of a characteristic diagram after convolution is consistent with that of input, and point-by-point addition calculation is used when the characteristic diagrams with the same size are fused in jump connection;
the improved UNet model uses an attention mechanism after the convolutional layer, including channel attention and spatial attention;
the channel attention uses global maximization to pool each channel of the feature map, outputs the attention weight of each channel after connecting the full connection layer, and multiplies the attention weight with the input feature map;
the spatial attention, use along the channel maximize pooling and along the channel average pooling to every space pixel position of the characteristic map, splice two characteristics according to the channel, output the attention weight of every space pixel position after connecting the convolution layer, then multiply with the input characteristic map;
the use of the channel attention and the spatial attention can improve the model performance, and is beneficial to model learning of feature representation which is more robust to identification and positioning.
When the water depth isodepth line is updated by the water surface area segmentation model, the latest reading of the water level gauge and the output mask of the water surface area segmentation model are received simultaneously, and the method specifically comprises the following steps:
the water depth isodepth line diagram is initialized when the water level meter reading exceeds a water depth threshold value for the first time, and the depth values of the output masks of the water surface area segmentation model are set as the current water level meter reading;
when receiving a new water surface area mask, the water depth isodepth line diagram calculates an intersection with the existing mask, and generates a water surface extension area at the moment after the intersection is subtracted from the new water surface area;
when a new water level meter reading is received, calculating a difference value from the previous reading, and taking the difference value as a depth value of a water surface extending area at the moment;
when a new water level reading is received, the depth value of different depth areas in the existing depth line diagram is updated by calculating the difference value from the previous reading, and the depth value of the different areas of the existing depth line diagram is added with the difference value to be used as a new depth value.
A water depth measuring method based on a water level gauge and a camera comprises the following steps:
s1: the background processing module regularly acquires the reading of the water level gauge, when the reading of the water level gauge is lower than a water depth threshold value, the water flooding problem does not occur, the camera is not started to take a candid photograph, and when the reading of the water level gauge is higher than the water depth threshold value, the water flooding problem occurs, and the camera is started to take a candid photograph;
s2: the camera acquires an area image of the water level gauge area in a snap shooting mode;
s3: the background processing module adopts an improved UNet model to divide a flooded area in a snap shot image of the camera;
s4: and the background processing module updates the depth contour line diagram according to the current reading of the water level gauge.
The invention has the following beneficial effects:
the method can automatically measure the depth of the flooded area and generate the isodepth line graph, does not need time-consuming and labor-consuming field survey of municipal workers, can provide a flooded profile for government departments, provides decision basis for traffic control, rescue and relief work, urban drainage and the like, and can also guide public to avoid danger and travel planning.
Drawings
Fig. 1 is a schematic diagram of the overall system of the present invention.
Fig. 2 is a system flow diagram of the present invention.
FIG. 3 is a graphical representation of the depth of water contour produced by the present invention.
Detailed Description
Embodiments of the present invention are described in further detail below with reference to the accompanying drawings.
As shown in fig. 1, a water depth measuring system based on a water level gauge and a camera comprises the following modules:
the water level gauge is used for measuring the water depth;
the water depth value transmission module is used for transmitting the measured water depth value of the water level gauge to the receiving module;
the camera is used for acquiring an area image of the water level gauge area;
the image transmission module is used for transmitting the area image data of the water level gauge area acquired by the camera to the receiving module;
the data receiving module is used for transmitting the received data to the background processing module;
and the background processing module is used for processing the water level gauge and camera data.
In an embodiment, the data source is water level gauge measurement water depth reading and regional image data.
In the embodiment, the camera acquires the image in a snap shooting mode, so that the calculated amount and the storage amount can be reduced compared with a video mode.
In an embodiment, the camera mounting height and angle cover the corresponding water level gauge area.
In an embodiment, the camera calibrates the covered water level gauge position.
In an embodiment, the water level gauge uses a wireless digital water level gauge, so that the water depth value can be conveniently acquired and transmitted.
In an embodiment, the water level gauge is used for transmitting water depth readings at fixed time and controlling whether the camera captures images or not;
the water level gauge is provided with a water depth threshold, when the water level gauge reading is smaller than the threshold, the camera does not do any work, when the water level gauge reading is larger than the water depth threshold, the camera captures images, and the current water level gauge reading and the camera capture images are transmitted to the background processing module through the receiving module.
In an embodiment, the background processing module includes a water surface area segmentation model for detecting a water surface area in an image and updating a water depth isocenter diagram according to a current water level meter reading.
In an embodiment, the water surface area segmentation model segments a flooded area in a snap shot image of a camera by adopting an improved UNet model, and specifically comprises the following steps:
the improved UNet model adopts zero padding in a convolution layer, the size of a characteristic diagram after convolution is consistent with that of input, and point-by-point addition calculation is used when the characteristic diagrams with the same size are fused in jump connection;
the improved UNet model uses an attention mechanism after the convolutional layer, including channel attention and spatial attention;
the channel attention uses global maximization to pool each channel of the feature map, outputs the attention weight of each channel after connecting the full connection layer, and multiplies the attention weight with the input feature map;
the spatial attention, use along the channel maximize pooling and along the channel average pooling to every space pixel position of the characteristic map, splice two characteristics according to the channel, output the attention weight of every space pixel position after connecting the convolution layer, then multiply with the input characteristic map;
the use of the channel attention and the spatial attention can improve the model performance, and is beneficial to model learning of feature representation which is more robust to identification and positioning.
In an embodiment, when the water surface area segmentation model updates the water depth isodepth line, the latest water level meter reading and the output mask of the water surface area segmentation model are received at the same time, and the specific steps are as follows:
the water depth isodepth line diagram is initialized when the water level meter reading exceeds a water depth threshold value for the first time, and the depth values of the output masks of the water surface area segmentation model are set as the current water level meter reading;
when receiving a new water surface area mask, the water depth isodepth line diagram calculates an intersection with the existing mask, and generates a water surface extension area at the moment after the intersection is subtracted from the new water surface area;
when a new water level meter reading is received, calculating a difference value from the previous reading, and taking the difference value as a depth value of a water surface extending area at the moment;
when a new water level reading is received, the depth value of different depth areas in the existing depth line diagram is updated by calculating the difference value from the previous reading, and the depth value of the different areas of the existing depth line diagram is added with the difference value to be used as a new depth value.
As shown in fig. 2, the water depth measuring method based on the water level gauge and the camera of the invention comprises the following steps:
s1: acquiring readings of a water level gauge at regular time;
in the embodiment, the background processing module obtains the reading of the wireless digital water level meter at regular time, sets a water depth threshold value, and when the reading of the water level meter is lower than the threshold value, the situation that flooding is not caused is indicated, the camera snapshot function is not started, and when the reading of the water level meter is higher than the threshold value, the situation that flooding is caused is indicated, and the camera is notified to start the snapshot function.
S2: capturing by a camera;
in the embodiment, the capturing mode is adopted for the camera to acquire the image, and the mode of decoding the video stream is not adopted, so that compared with the video mode, the calculated amount and the storage amount can be reduced.
S3: dividing a water surface area;
in an embodiment, the water surface area segmentation adopts an improved UNet model to segment a flooded area in a snap shot image of a camera, and specifically comprises the following steps:
the improved UNet model adopts zero padding in a convolution layer, the size of a characteristic diagram after convolution is consistent with that of input, and point-by-point addition calculation is used when the characteristic diagrams with the same size are fused in jump connection;
the improved UNet model uses an attention mechanism after the convolutional layer, including channel attention and spatial attention;
the channel attention uses global maximization to pool each channel of the feature map, outputs the attention weight of each channel after connecting the full connection layer, and multiplies the attention weight with the input feature map;
the spatial attention, use along the channel maximize pooling and along the channel average pooling to every space pixel position of the characteristic map, splice two characteristics according to the channel, output the attention weight of every space pixel position after connecting the convolution layer, then multiply with the input characteristic map;
the use of the channel attention and the spatial attention can improve the model performance, and is beneficial to model learning of feature representation which is more robust to identification and positioning.
S4: updating the isocenter diagram;
in an embodiment, the depth contour line update receives the latest water level meter reading and the output mask of the water surface area segmentation model at the same time, and the specific steps are as follows:
the water depth isodepth line diagram is initialized when the water level meter reading exceeds a water depth threshold value for the first time, and the depth values of the output masks of the water surface area segmentation model are set as the current water level meter reading;
when receiving a new water surface area mask, the water depth isodepth line diagram calculates an intersection with the existing mask, and generates a water surface extension area at the moment after the intersection is subtracted from the new water surface area;
when a new water level meter reading is received, calculating a difference value from the previous reading, and taking the difference value as a depth value of a water surface extending area at the moment;
when a new water level reading is received, the depth value of different depth areas in the existing depth line diagram is updated by calculating the difference value from the previous reading, and the depth value of the different areas of the existing depth line diagram is added with the difference value to be used as a new depth value. A water depth isocenter diagram in the embodiment of the invention is shown in FIG. 3.
The above is only a preferred embodiment of the present invention, and the protection scope of the present invention is not limited to the above examples, and all technical solutions belonging to the concept of the present invention belong to the protection scope of the present invention. It should be noted that modifications and adaptations to the invention without departing from the principles thereof are intended to be within the scope of the invention as set forth in the following claims.
Claims (6)
1. A water depth measurement system based on a water level gauge and a camera, comprising the following modules:
the water level gauge is used for measuring the water depth;
the water depth value transmission module is used for transmitting the measured water depth value of the water level gauge to the receiving module;
the camera is used for acquiring an area image of the water level gauge area;
the image transmission module is used for transmitting the area image data of the water level gauge area acquired by the camera to the receiving module;
the data receiving module is used for transmitting the received data to the background processing module;
the background processing module is used for processing the water level gauge and camera data;
the water level meter is used for transmitting water depth readings at fixed time and controlling whether the camera captures images or not;
the water level gauge is provided with a water depth threshold, when the water level gauge reading is smaller than the threshold, the camera does not do any work, when the water level gauge reading is larger than the water depth threshold, the camera captures images, and the current water level gauge reading and the camera capturing images are transmitted to the background processing module through the receiving module;
the background processing module comprises a water surface area segmentation model and is used for detecting a water surface area in an image and updating a water depth isodepth line graph according to the current reading of the water level gauge;
the water surface area segmentation model adopts an improved UNet model to segment a flooded area in a snap shot image of a camera, and specifically comprises the following steps:
the improved UNet model adopts zero padding in a convolution layer, the size of a characteristic diagram after convolution is consistent with that of input, and point-by-point addition calculation is used when the characteristic diagrams with the same size are fused in jump connection;
the improved UNet model uses an attention mechanism after the convolutional layer, including channel attention and spatial attention;
the channel attention uses global maximization to pool each channel of the feature map, outputs the attention weight of each channel after connecting the full connection layer, and multiplies the attention weight with the input feature map;
the spatial attention, use along the channel maximize pooling and along the channel average pooling to every space pixel position of the characteristic map, splice two characteristics according to the channel, output the attention weight of every space pixel position after connecting the convolution layer, then multiply with the input characteristic map;
the use of the channel attention and the spatial attention can improve the performance of the model, and is beneficial to the model learning of the feature representation which is more robust to identification and positioning;
when the water surface area segmentation model updates the water depth isodepth line, the latest reading of the water level gauge and the output mask of the water surface area segmentation model are received simultaneously, and the method comprises the following specific steps:
the water depth isodepth line diagram is initialized when the water level meter reading exceeds a water depth threshold value for the first time, and the depth values of the output masks of the water surface area segmentation model are set as the current water level meter reading;
when receiving a new water surface area mask, the water depth isodepth line diagram calculates an intersection with the existing mask, and generates a water surface extension area at the moment after the intersection is subtracted from the new water surface area;
when a new water level meter reading is received, calculating a difference value from the previous reading, and taking the difference value as a depth value of a water surface extending area at the moment;
when a new water level reading is received, the depth value of different depth areas in the existing depth line diagram is updated by calculating the difference value from the previous reading, and the depth value of the different areas of the existing depth line diagram is added with the difference value to be used as a new depth value.
2. The water depth measuring system based on a water level gauge and a camera according to claim 1, wherein the camera acquires images in a snap shot manner.
3. A water depth measuring system based on a water level gauge and a camera according to claim 1, wherein the camera is mounted at a height and angle to cover the corresponding water level gauge area.
4. A water depth measuring system based on a water level gauge and a camera according to claim 3, wherein the camera calibrates the covered water level gauge position.
5. A water depth measuring system based on a water level gauge and a camera according to claim 1, wherein the water level gauge uses a wireless digital water level gauge.
6. A water depth measuring method based on a water level gauge and a camera, realized based on the system of any one of claims 1-5, characterized by comprising the following steps:
s1: the background processing module regularly acquires the reading of the water level gauge, when the reading of the water level gauge is lower than a water depth threshold value, the water flooding problem does not occur, the camera is not started to take a candid photograph, and when the reading of the water level gauge is higher than the water depth threshold value, the water flooding problem occurs, and the camera is started to take a candid photograph;
s2: the camera acquires an area image of the water level gauge area in a snap shooting mode;
s3: the background processing module adopts an improved UNet model to divide a flooded area in a snap shot image of the camera;
s4: and the background processing module updates the depth contour line diagram according to the current reading of the water level gauge.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110712712.6A CN113421299B (en) | 2021-06-25 | 2021-06-25 | Water depth measuring system and method based on water level gauge and camera |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110712712.6A CN113421299B (en) | 2021-06-25 | 2021-06-25 | Water depth measuring system and method based on water level gauge and camera |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113421299A CN113421299A (en) | 2021-09-21 |
| CN113421299B true CN113421299B (en) | 2024-03-29 |
Family
ID=77717661
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110712712.6A Active CN113421299B (en) | 2021-06-25 | 2021-06-25 | Water depth measuring system and method based on water level gauge and camera |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113421299B (en) |
Citations (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2006010483A (en) * | 2004-06-25 | 2006-01-12 | Senaa Kk | Method and apparatus for updating information on bottom of water |
| WO2007032595A1 (en) * | 2005-09-16 | 2007-03-22 | Korea Institute Of Construction Technology | System and method for measuring liquid level by image |
| CN102663827A (en) * | 2012-03-02 | 2012-09-12 | 天津大学 | Three-dimensional dynamic whole-process simulation method for storm surge and flood routing in complex flooding areas |
| JP2012185061A (en) * | 2011-03-07 | 2012-09-27 | Mitsubishi Electric Corp | Water level detection device, water level detection system, and water level detection method |
| CN104794753A (en) * | 2015-04-29 | 2015-07-22 | 武汉大学 | Earth rock cofferdam breach flood risk mapping method |
| CN107564052A (en) * | 2017-08-10 | 2018-01-09 | 张立华 | A kind of security assessment method of nautical chart isobath abbreviation |
| CN208172857U (en) * | 2018-02-11 | 2018-11-30 | 南昌市气象局 | A kind of Meteorological Risk Analysis early warning system of urban waterlogging disaster |
| JP2020060463A (en) * | 2018-10-11 | 2020-04-16 | 古野電気株式会社 | Underwater sensor and underwater sensing method |
| CN111080541A (en) * | 2019-12-06 | 2020-04-28 | 广东启迪图卫科技股份有限公司 | Color image denoising method based on bit layering and attention fusion mechanism |
| CN111414504A (en) * | 2020-05-08 | 2020-07-14 | 刘克建 | Building site flood detection system based on block chain and CIM |
| CN112013921A (en) * | 2019-05-30 | 2020-12-01 | 杭州海康威视数字技术股份有限公司 | Method, device and system for acquiring water level information based on water level gauge measurement image |
| CN112598910A (en) * | 2020-11-16 | 2021-04-02 | 河北工程大学 | Guiding method and device for street ponding early warning |
| CN113012172A (en) * | 2021-04-09 | 2021-06-22 | 杭州师范大学 | AS-UNet-based medical image segmentation method and system |
-
2021
- 2021-06-25 CN CN202110712712.6A patent/CN113421299B/en active Active
Patent Citations (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2006010483A (en) * | 2004-06-25 | 2006-01-12 | Senaa Kk | Method and apparatus for updating information on bottom of water |
| WO2007032595A1 (en) * | 2005-09-16 | 2007-03-22 | Korea Institute Of Construction Technology | System and method for measuring liquid level by image |
| JP2012185061A (en) * | 2011-03-07 | 2012-09-27 | Mitsubishi Electric Corp | Water level detection device, water level detection system, and water level detection method |
| CN102663827A (en) * | 2012-03-02 | 2012-09-12 | 天津大学 | Three-dimensional dynamic whole-process simulation method for storm surge and flood routing in complex flooding areas |
| CN104794753A (en) * | 2015-04-29 | 2015-07-22 | 武汉大学 | Earth rock cofferdam breach flood risk mapping method |
| CN107564052A (en) * | 2017-08-10 | 2018-01-09 | 张立华 | A kind of security assessment method of nautical chart isobath abbreviation |
| CN208172857U (en) * | 2018-02-11 | 2018-11-30 | 南昌市气象局 | A kind of Meteorological Risk Analysis early warning system of urban waterlogging disaster |
| JP2020060463A (en) * | 2018-10-11 | 2020-04-16 | 古野電気株式会社 | Underwater sensor and underwater sensing method |
| CN112013921A (en) * | 2019-05-30 | 2020-12-01 | 杭州海康威视数字技术股份有限公司 | Method, device and system for acquiring water level information based on water level gauge measurement image |
| CN111080541A (en) * | 2019-12-06 | 2020-04-28 | 广东启迪图卫科技股份有限公司 | Color image denoising method based on bit layering and attention fusion mechanism |
| CN111414504A (en) * | 2020-05-08 | 2020-07-14 | 刘克建 | Building site flood detection system based on block chain and CIM |
| CN112598910A (en) * | 2020-11-16 | 2021-04-02 | 河北工程大学 | Guiding method and device for street ponding early warning |
| CN113012172A (en) * | 2021-04-09 | 2021-06-22 | 杭州师范大学 | AS-UNet-based medical image segmentation method and system |
Non-Patent Citations (10)
| Title |
|---|
| Birkett CM..Synergistic remote sensing of Lake Chad: Variability of basin inundation.Remote Sensing of Environment.2000,72(2),全文. * |
| Bulk and Export Production Fluxes in the Gulf of Aqaba, Northern Red Sea;ACS Earth and Space Chemistry;4(8);全文 * |
| Fast Computation of 2-Dimensional Depth Contours;Ted Johnson;Ivy Kwok;Raymond Ng;Knowledge Discovery & Data Mining Conferences 1995-1998;20091231;全文 * |
| S-57格式海图等深线数据向Shape格式的转换;高敏; 罗毅;第十八届中国环境遥感应用技术论坛论文集;全文 * |
| Synergistic remote sensing of Lake Chad: Variability of basin inundation;Birkett CM.;Remote Sensing of Environment;72(2);全文 * |
| 新型等深线生成方法研究与应用;王海涛; 李剑; 黄第科;中国水运;全文 * |
| 欧洲城市洪水管理决策支持系统;童国庆;;水利水电快报(第08期);全文 * |
| 水位图像识别的场景问题处理方法和技术;江海洋;刘林海;李红石;;水利信息化;20200225(第01期);全文 * |
| 洞里萨湖水位与面积和容积的关系研究;李昌文;徐照明;甘拯;游中琼;马强;;人民长江(第04期);全文 * |
| 融合深度与肤色特征的自适应手部跟踪算法;钮晨霄;孙瑾;丁永晖;;计算机科学;20160615(第S1期);全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113421299A (en) | 2021-09-21 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111879292B (en) | Coastline dynamic monitoring method, coastline dynamic monitoring equipment and storage medium | |
| CN112362900A (en) | Unattended water level flow velocity monitoring camera and monitoring method | |
| CN114333243A (en) | Landslide monitoring and early warning method, device, medium, electronic equipment and terminal | |
| CN113808263B (en) | Map generation data collection device and map generation data collection method | |
| JP7023803B2 (en) | Monitoring system | |
| CN111275930A (en) | Drowning-prevention wearable equipment control system and method thereof | |
| JP2014119266A (en) | Water management system and method | |
| CN113421299B (en) | Water depth measuring system and method based on water level gauge and camera | |
| CN116153140A (en) | River basin emergency unmanned aerial vehicle management method and platform | |
| CN105761275A (en) | Fire-fighting early warning aircraft with binocular visual structure | |
| CN113965733A (en) | Binocular video monitoring method, system, computer equipment and storage medium | |
| CN114067533A (en) | Geological disaster photographing monitoring and early warning method | |
| CN108229240A (en) | A kind of method and device of determining picture quality | |
| CN117152617A (en) | Urban flood identification method and system | |
| CN117372629A (en) | Reservoir visual data supervision control system and method based on digital twinning | |
| US11995864B2 (en) | System and method for localisation using footprints | |
| TWI481824B (en) | Method of water level surveillance | |
| CN113689493A (en) | Lens attachment detection method, lens attachment detection device, electronic equipment and storage medium | |
| CN114235082B (en) | Intelligent metering method based on sand production monitoring system | |
| CN113744393B (en) | Multi-level slope landslide change monitoring method | |
| CN116246090A (en) | System and method for identifying target based on example segmentation and infrared sensor | |
| KR102377929B1 (en) | System and method for measuring water level based on neural network module | |
| CN114694073A (en) | Intelligent detection method and device for wearing condition of safety belt, storage medium and equipment | |
| JP2012203722A (en) | Feature selection system, feature selection program, and feature selection method | |
| CN117516487B (en) | Medium-small river video flow test 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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |