CN111142150A - Automatic intelligent obstacle avoidance design method for seismic exploration - Google Patents
Automatic intelligent obstacle avoidance design method for seismic exploration Download PDFInfo
- Publication number
- CN111142150A CN111142150A CN202010013160.5A CN202010013160A CN111142150A CN 111142150 A CN111142150 A CN 111142150A CN 202010013160 A CN202010013160 A CN 202010013160A CN 111142150 A CN111142150 A CN 111142150A
- Authority
- CN
- China
- Prior art keywords
- obstacles
- seismic exploration
- neural network
- automatic intelligent
- satellite
- 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
- 238000013461 design Methods 0.000 title claims abstract description 26
- 238000000034 method Methods 0.000 title claims abstract description 26
- 238000012549 training Methods 0.000 claims abstract description 18
- 238000003062 neural network model Methods 0.000 claims abstract description 16
- 238000013528 artificial neural network Methods 0.000 claims abstract description 15
- 238000002372 labelling Methods 0.000 claims abstract description 10
- 238000013507 mapping Methods 0.000 claims abstract description 5
- 239000000523 sample Substances 0.000 claims description 23
- 239000003086 colorant Substances 0.000 claims description 12
- 238000001514 detection method Methods 0.000 claims description 6
- 230000004888 barrier function Effects 0.000 claims description 5
- 239000003550 marker Substances 0.000 claims description 5
- 238000012545 processing Methods 0.000 claims description 3
- 238000010586 diagram Methods 0.000 description 5
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 4
- 238000010276 construction Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000005284 excitation Effects 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01V—GEOPHYSICS; GRAVITATIONAL MEASUREMENTS; DETECTING MASSES OR OBJECTS; TAGS
- G01V1/00—Seismology; Seismic or acoustic prospecting or detecting
- G01V1/003—Seismic data acquisition in general, e.g. survey design
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
- G05D1/00—Control of position, course, altitude or attitude of land, water, air or space vehicles, e.g. using automatic pilots
- G05D1/0088—Control of position, course, altitude or attitude of land, water, air or space vehicles, e.g. using automatic pilots characterized by the autonomous decision making process, e.g. artificial intelligence, predefined behaviours
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
- G05D1/00—Control of position, course, altitude or attitude of land, water, air or space vehicles, e.g. using automatic pilots
- G05D1/02—Control of position or course in two dimensions
- G05D1/021—Control of position or course in two dimensions specially adapted to land vehicles
Landscapes
- Engineering & Computer Science (AREA)
- Remote Sensing (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Aviation & Aerospace Engineering (AREA)
- Radar, Positioning & Navigation (AREA)
- Automation & Control Theory (AREA)
- Life Sciences & Earth Sciences (AREA)
- Evolutionary Computation (AREA)
- Artificial Intelligence (AREA)
- Health & Medical Sciences (AREA)
- Game Theory and Decision Science (AREA)
- Medical Informatics (AREA)
- Business, Economics & Management (AREA)
- Acoustics & Sound (AREA)
- Environmental & Geological Engineering (AREA)
- Geology (AREA)
- General Life Sciences & Earth Sciences (AREA)
- Geophysics (AREA)
- Geophysics And Detection Of Objects (AREA)
Abstract
The invention provides a seismic exploration automatic intelligent obstacle avoidance design method, which comprises the following steps: step 1, acquiring a ground object mark map and a satellite picture within a work area range; step 2, extracting obstacle information and corresponding satellite picture pixel values in the surface feature labeling map, and constructing a training sample library of different obstacles; step 3, carrying out neural network training on the sample library to obtain neural network model parameters; step 4, automatically identifying satellite pictures in the whole work area range; and 5, automatically avoiding obstacles for the shot points according to the recognition result. The automatic intelligent obstacle avoidance design method for seismic exploration trains the mapping relation between ground object marking information and corresponding satellite picture pixel values through the neural network, and then automatically identifies and classifies obstacles in the whole work area satellite picture through the trained neural network, so that the problem of identification and classification of various obstacles in the satellite picture is well solved.
Description
Technical Field
The invention relates to the field of oil-gas seismic exploration data acquisition, in particular to an automatic intelligent obstacle avoidance design method for seismic exploration.
Background
The design of the observation system plays an important role in seismic data acquisition, and the design of an indoor observation system can be generally carried out according to geological requirements of exploration. In general, the obstacle distribution condition of an actual construction area is not considered in the design of an indoor observation system, which causes a difference between the actual construction and the design of the observation system. In order to design an observation system which is more suitable for actual conditions, the indoor observation system can be designed to be changed through a satellite map, and common obstacles such as buildings, factories, villages, water areas and the like are avoided. At present, the obstacle avoidance design is mainly realized through manual adjustment, and shot and inspection points are prevented from being arranged in an area where excitation receiving cannot be carried out. Such manual operations are labor intensive and sometimes difficult to operate accurately when the work area is large. There is also a method for automatically identifying obstacles and designing obstacle avoidance of an observation system by using a satellite map, but the automatic identification of the obstacles is difficult because of the great difference of the characteristics of similar objects in the actual satellite map (for example, the colors of a water area are distinguished by blue, green, yellow and the like due to different water qualities). Therefore, a novel automatic intelligent obstacle avoidance design method for seismic exploration is invented, and the technical problems are solved.
Disclosure of Invention
The invention aims to provide an automatic intelligent obstacle avoidance design method for seismic exploration, which solves the problem of identification and classification of various obstacles in a satellite picture.
The object of the invention can be achieved by the following technical measures: the automatic intelligent obstacle avoidance design method for seismic exploration comprises the following steps: step 1, acquiring a ground object mark map and a satellite picture within a work area range; step 2, extracting obstacle information and corresponding satellite picture pixel values in the surface feature labeling map, and constructing a training sample library of different obstacles; step 3, carrying out neural network training on the sample library to obtain neural network model parameters; step 4, automatically identifying satellite pictures in the whole work area range; and 5, automatically avoiding obstacles for the shot points according to the recognition result.
The object of the invention can also be achieved by the following technical measures:
in step 1, the landmark signature map corresponds to the satellite picture.
In step 1, the acquired ground feature marking map and the satellite picture carry coordinate information, and the marking information can be directly read from the ground feature marking map file.
In step 2, different surface features on the surface feature marking map have different colors, and typical seismic exploration obstacles with marks are identified on the surface feature marking map based on the characteristics.
In step 2, the pixel values of the satellite pictures at the positions corresponding to the obstacles are obtained, the mapping relation between the pixel values and the types of the obstacles is established, and training sample libraries of different obstacles are constructed.
In step 3, the sample library is trained by using a neural network model, the pixel value of the obstacle on the satellite picture is used as the input of the neural network, and the type of the obstacle is used as the output of the neural network.
In step 4, the trained neural network model automatically identifies and classifies the obstacles on the satellite map in the whole work area.
The automatic intelligent obstacle avoidance design method for seismic exploration further comprises the step 4 of marking the obstacle identification result, marking the obstacle and the safety range by using the color 1, marking the area of the encrypted shot point by using the color 2, and marking the area without the obstacle by using the color 3.
In the step 5, when the observation system is arranged, corresponding processing is carried out according to different marking colors of the positions of the point locations, the color 3 area is normally arranged, the color 1 area is removed, and the color 2 area is encrypted, so that the automatic intelligent obstacle avoidance design of seismic exploration is realized.
In the step 5, the point location comprises a shot point position and a wave detection point position, and the point location encryption is to move the shot point or the wave detection point in the barrier into a safety area and keep the total number of the shot point or the wave detection point unchanged; point location encryption follows the following rules: the demodulator probe is along the direction vertical to the measuring line, the shot point is along the measuring line, and the distance from the encrypted position to the original position cannot exceed half of the side length of the longitudinal and transverse surface elements; if the barrier still can not be avoided, a principle of moving nearby is adopted, and two shot points can not appear in the same surface element after moving.
The automatic intelligent obstacle avoidance design method for seismic exploration is mainly used for data acquisition in seismic exploration. The method comprises the steps of firstly obtaining a ground object marking map and satellite pictures in a work area range and nearby, wherein different ground objects on the ground object marking map have different colors, identifying typical seismic exploration obstacles with marks on the ground object marking map based on the characteristic, simultaneously obtaining satellite picture pixel values of corresponding positions of the obstacles, establishing a training sample library of different obstacles, training by using a neural network model, automatically identifying and classifying the obstacles on the satellite map in the whole work area by using the trained neural network model, marking the obstacles and a safety range by using red, marking an area with encrypted shot points by using green, and marking an area without the obstacles by using black. When the observation system is arranged, corresponding processing is carried out according to different marking colors of the positions of the point locations, the black areas are normally arranged, the red areas are removed, and the green areas are encrypted, so that the automatic intelligent obstacle avoidance design of seismic exploration is realized.
Compared with the prior art, the invention has the beneficial effects that: the method is characterized in that a ground object labeling map and Google satellite pictures are jointly applied to automatically and intelligently identify the obstacles, the ground object labeling map labels buildings, villages, road networks and water areas in most areas with dense population, but labeling information is incomplete in the areas with less population distribution, and the ground object labeling map is used for automatically identifying the obstacles, so that a large error exists. The method has the advantages that the detailed satellite image data are available in most regions of the earth suitable for exploration, so that the mapping relation between the ground object labeling information and the corresponding satellite picture pixel values is trained through the neural network, then the trained neural network is used for automatically identifying and classifying the obstacles in the satellite picture of the whole work area, and the problem of identification and classification of various obstacles in the satellite picture is well solved.
Drawings
FIG. 1 is a map (local) of landmark markers in a work area A in accordance with an embodiment of the present invention;
FIG. 2 is a diagram illustrating the result (partial) of automatic obstacle identification in the work area A according to an embodiment of the present invention;
FIG. 3 is a diagram illustrating an automatic obstacle avoidance result (local) of an obstacle in the work area A according to an embodiment of the present invention;
FIG. 4 is a map (local) of landmark markers in work area A in accordance with an embodiment of the present invention;
FIG. 5 is a diagram illustrating the result (partial) of automatic obstacle identification in the work area A according to an embodiment of the present invention;
FIG. 6 is a diagram illustrating an automatic obstacle avoidance result (local) of an obstacle in the working area A according to an embodiment of the present invention;
FIG. 7 is a flowchart of an embodiment of an automatic intelligent obstacle avoidance design method for seismic exploration according to the present invention.
Detailed Description
In order to make the aforementioned and other objects, features and advantages of the present invention comprehensible, preferred embodiments accompanied with figures are described in detail below.
As shown in fig. 7, fig. 7 is a structural diagram of the automatic intelligent obstacle avoidance design method for seismic exploration according to the present invention.
the obtained ground object marking map and the satellite picture have coordinate information, and the marking information can be directly read from the ground object marking map file;
102, identifying typical seismic exploration obstacles with marks on a ground object marking map, wherein different ground objects on the ground object marking map have different colors;
103, acquiring the pixel values of the satellite pictures at the positions corresponding to the obstacles in the step 102, establishing a mapping relation between the pixel values and the types of the obstacles, and constructing training sample libraries of different obstacles;
104, training the sample library in the step 103 by using a neural network model; training the sample library in the step 103 by using a neural network model, wherein the pixel value of the obstacle on the satellite image is used as the input of the neural network, and the type of the obstacle is used as the output of the neural network;
training the sample library in the step 103 by using a neural network model, wherein the adopted neural network model is not limited and can be selected according to actual conditions;
105, automatically identifying and classifying obstacles on a satellite map in the whole work area by the trained neural network model;
and 106, marking the obstacle identification result, marking the obstacle and the safety range by using red, marking the area of the encrypted shot point by using green, and marking the area without the obstacle by using black. The safety range of the obstacle is set according to the type of the obstacle and needs to be preset.
The obstacle recognition results are labeled, and the colors of the labels of the different recognition results are not limited to those described in step 106, as long as the different recognition results can be distinguished.
And 107, when the observation system is arranged, carrying out corresponding treatment according to different marking colors of the positions of the point locations, wherein black areas are normally arranged, red areas are removed, and green areas are subjected to point location encryption, so that the automatic intelligent obstacle avoidance design of seismic exploration is realized.
The point location includes a shot point location and a demodulator probe location, and the colors of different regions must be strictly corresponding to the colors marked in step 6.
The point encryption is to move the shot point or the demodulator probe in the barrier into a safe area and keep the total number of the shot point or the demodulator probe unchanged as much as possible. Point location encryption is also according to the following rules: the demodulator probe is along the direction vertical to the measuring line, the shot point is along the measuring line, and the distance from the encrypted position to the original position cannot exceed half of the side length of the longitudinal and transverse surface elements; if the barrier still can not be avoided, a principle of moving nearby is adopted, and two shot points can not appear in the same surface element after moving.
The following are two specific examples to which the present invention is applied.
Example 1 (work site a):
(1) acquiring a ground object mark map (shown in figure 1) and a satellite picture within the range of the work area A;
(2) extracting obstacle information and corresponding satellite picture pixel values in a ground object labeling map, and constructing a training sample library of different obstacles (1000000 groups of obstacle samples are extracted in embodiment 1);
(3) carrying out neural network training on the sample library to obtain neural network model parameters;
(4) and automatically identifying the satellite pictures in the whole work area range, wherein the identification result is shown in figure 2.
(5) And automatically avoiding the obstacle of the shot point according to the recognition result, which is shown in figure 3.
Example 2(B work area):
(1) acquiring a ground object mark map (shown in figure 4) and a satellite picture within the range of the work area B;
(2) extracting obstacle information and corresponding satellite picture pixel values in a ground object labeling map, and constructing a training sample library of different obstacles (1000000 groups of obstacle samples are extracted in embodiment 2);
(3) carrying out neural network training on the sample library to obtain neural network model parameters;
(4) and automatically identifying the satellite pictures in the whole work area range, wherein an identification result is shown in figure 5.
(5) And automatically avoiding the obstacle of the shot point according to the recognition result, which is shown in figure 6.
Claims (10)
1. The automatic intelligent obstacle avoidance design method for seismic exploration is characterized by comprising the following steps of:
step 1, acquiring a ground object mark map and a satellite picture within a work area range;
step 2, extracting obstacle information and corresponding satellite picture pixel values in the surface feature labeling map, and constructing a training sample library of different obstacles;
step 3, carrying out neural network training on the sample library to obtain neural network model parameters;
step 4, automatically identifying satellite pictures in the whole work area range;
and 5, automatically avoiding obstacles for the shot points according to the recognition result.
2. The method for designing the automatic intelligent obstacle avoidance for the seismic exploration, according to claim 1, is characterized in that in step 1, the ground object marker map corresponds to the satellite picture.
3. The method for designing the automatic intelligent obstacle avoidance for the seismic exploration, according to claim 1, is characterized in that in step 1, the obtained ground object marker map and the satellite picture have coordinate information, and the marker information can be directly read from a ground object marker map file.
4. The method as claimed in claim 1, wherein in step 2, different surface features on the surface feature map have different colors, and typical seismic exploration obstacles with marks are identified on the surface feature map based on the color features.
5. The method for designing the automatic intelligent obstacle avoidance for the seismic exploration, according to claim 1, is characterized in that in step 2, the pixel values of the satellite pictures at the positions corresponding to the obstacles are obtained, the mapping relation between the pixel values and the types of the obstacles is established, and training sample libraries of different obstacles are constructed.
6. An automatic intelligent obstacle avoidance design method for seismic exploration according to claim 1, wherein in step 3, a neural network model is used to train a sample base, the pixel value of an obstacle on a satellite image is used as the input of the neural network, and the type of the obstacle is used as the output of the neural network.
7. The automatic intelligent obstacle avoidance design method for seismic exploration according to claim 1, wherein in step 4, the trained neural network model automatically identifies and classifies obstacles on a satellite map in the whole work area.
8. The method for designing the automatic intelligent obstacle avoidance for the seismic exploration, according to the claim 1, is characterized by further comprising the step of marking the identification result of the obstacle after the step 4, marking the obstacle and the safety range by using the color 1, marking the area of the encrypted shot point by using the color 2, and marking the area without the obstacle by using the color 3.
9. The method as claimed in claim 8, wherein in step 5, when the observation system is deployed, corresponding processing is performed according to different marking colors of the positions of the points, the area with the color 3 is normally deployed, the area with the color 1 is removed, and the area with the color 2 is encrypted, so that the automatic intelligent obstacle avoidance design for seismic exploration is realized.
10. The automatic intelligent obstacle avoidance design method for seismic exploration according to claim 9, wherein in the step 5, the point location comprises a shot point location and a wave detection point location, and the point location encryption is to move the shot point or the wave detection point in the obstacle into a safe area and keep the total number of the shot point or the wave detection point unchanged; point location encryption follows the following rules: the demodulator probe is along the direction vertical to the measuring line, the shot point is along the measuring line, and the distance from the encrypted position to the original position cannot exceed half of the side length of the longitudinal and transverse surface elements; if the barrier still can not be avoided, a principle of moving nearby is adopted, and two shot points can not appear in the same surface element after moving.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010013160.5A CN111142150A (en) | 2020-01-06 | 2020-01-06 | Automatic intelligent obstacle avoidance design method for seismic exploration |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010013160.5A CN111142150A (en) | 2020-01-06 | 2020-01-06 | Automatic intelligent obstacle avoidance design method for seismic exploration |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111142150A true CN111142150A (en) | 2020-05-12 |
Family
ID=70523808
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010013160.5A Pending CN111142150A (en) | 2020-01-06 | 2020-01-06 | Automatic intelligent obstacle avoidance design method for seismic exploration |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111142150A (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106291671A (en) * | 2015-06-27 | 2017-01-04 | 中国石油化工股份有限公司 | A kind of automatic troubleshooting method of stereo observing system based on satellite image data |
| CN106778548A (en) * | 2016-11-30 | 2017-05-31 | 百度在线网络技术（北京）有限公司 | Method and apparatus for detecting barrier |
| CN108197569A (en) * | 2017-12-29 | 2018-06-22 | 驭势科技（北京）有限公司 | Obstacle recognition method, device, computer storage media and electronic equipment |
| CN108470185A (en) * | 2018-02-12 | 2018-08-31 | 北京佳格天地科技有限公司 | The atural object annotation equipment and method of satellite image |
| CN110244760A (en) * | 2019-06-06 | 2019-09-17 | 深圳市道通智能航空技术有限公司 | A kind of barrier-avoiding method, device and electronic equipment |
-
2020
- 2020-01-06 CN CN202010013160.5A patent/CN111142150A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106291671A (en) * | 2015-06-27 | 2017-01-04 | 中国石油化工股份有限公司 | A kind of automatic troubleshooting method of stereo observing system based on satellite image data |
| CN106778548A (en) * | 2016-11-30 | 2017-05-31 | 百度在线网络技术（北京）有限公司 | Method and apparatus for detecting barrier |
| CN108197569A (en) * | 2017-12-29 | 2018-06-22 | 驭势科技（北京）有限公司 | Obstacle recognition method, device, computer storage media and electronic equipment |
| CN108470185A (en) * | 2018-02-12 | 2018-08-31 | 北京佳格天地科技有限公司 | The atural object annotation equipment and method of satellite image |
| CN110244760A (en) * | 2019-06-06 | 2019-09-17 | 深圳市道通智能航空技术有限公司 | A kind of barrier-avoiding method, device and electronic equipment |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Garilli et al. | Automatic detection of stone pavement's pattern based on UAV photogrammetry | |
| CN108765404A (en) | A kind of road damage testing method and device based on deep learning image classification | |
| CN111025286B (en) | Ground penetrating radar map self-adaptive selection method for water damage detection | |
| CN110133639B (en) | Dowel bar construction quality detection method | |
| US11941878B2 (en) | Automated computer system and method of road network extraction from remote sensing images using vehicle motion detection to seed spectral classification | |
| Almeer | Vegetation extraction from free google earth images of deserts using a robust BPNN approach in HSV Space | |
| CN115690081A (en) | Tree counting method, system, storage medium, computer equipment and terminal | |
| CN109255279A (en) | A kind of method and system of road traffic sign detection identification | |
| Shokri et al. | A robust and efficient method for power lines extraction from mobile LiDAR point clouds | |
| CN116246181A (en) | Extra-high voltage dense channel drift monitoring method based on satellite remote sensing technology | |
| CN114266893A (en) | Smoke and fire hidden danger identification method and device | |
| CN111025285A (en) | Asphalt pavement water damage detection method based on map gray scale self-adaptive selection | |
| CN112613437B (en) | Method for identifying illegal buildings | |
| CN110716199B (en) | Geological radar marking method for automatically distinguishing multiple types of defects by computer | |
| CN111142150A (en) | Automatic intelligent obstacle avoidance design method for seismic exploration | |
| CN116823896A (en) | Target mining area range prediction method and device under high vegetation coverage and electronic equipment | |
| CN113538385B (en) | Tunnel apparent disease type and grade discrimination method based on deep learning | |
| Kasemsuppakorn et al. | Pedestrian network extraction from fused aerial imagery (orthoimages) and laser imagery (lidar) | |
| Kaur et al. | Automatic road detection of satellite images—A survey | |
| Rettelbach et al. | From images to hydrologic networks-understanding the arctic landscape with graphs | |
| Cuypers et al. | Planimetric Rail Positioning Using Uav Photogrammetry: Towards Automated and Safe Railway Infrastructure Monitoring | |
| Idris et al. | Application of artificial neural network for building feature extraction in Abuja | |
| Eiseman et al. | Automatic odometry-less opendrive generation from sparse point clouds | |
| CN113536860B (en) | Key frame extraction method, and vectorization method of road traffic equipment and facilities | |
| Gromov et al. | Analysis and object markup of hyperspectral images for machine learning methods |
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: 20200512 |
|
| RJ01 | Rejection of invention patent application after publication |