CN115359359A - Oil storage tank detection method and device based on remote sensing image - Google Patents
Oil storage tank detection method and device based on remote sensing image Download PDFInfo
- Publication number
- CN115359359A CN115359359A CN202211166207.7A CN202211166207A CN115359359A CN 115359359 A CN115359359 A CN 115359359A CN 202211166207 A CN202211166207 A CN 202211166207A CN 115359359 A CN115359359 A CN 115359359A
- Authority
- CN
- China
- Prior art keywords
- storage tank
- oil storage
- prediction frame
- prediction
- frame set
- 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
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/10—Terrestrial scenes
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/255—Detecting or recognising potential candidate objects based on visual cues, e.g. shapes
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/82—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using neural networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V2201/00—Indexing scheme relating to image or video recognition or understanding
- G06V2201/07—Target detection
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Evolutionary Computation (AREA)
- Health & Medical Sciences (AREA)
- Artificial Intelligence (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Computing Systems (AREA)
- Databases & Information Systems (AREA)
- General Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Software Systems (AREA)
- Image Analysis (AREA)
Abstract
The application provides an oil storage tank detection method and device based on remote sensing images, and relates to the technical field of remote sensing image processing, wherein the method comprises the following steps: processing the remote sensing image by utilizing a previously trained YOLOv5 model to obtain a first oil storage tank prediction frame set; filtering the first oil storage tank prediction frame set by utilizing non-maximum value inhibition to obtain a second oil storage tank prediction frame set; acquiring the width-height and the width-height ratio of each oil storage tank prediction frame in the second oil storage tank prediction frame set, and removing the oil storage tank prediction frame from the second oil storage tank prediction frame set to obtain a third oil storage tank prediction frame set when the width-height of one oil storage tank prediction frame is not up to a preset width-height threshold value or the width-height ratio is not in a preset interval; and detecting and removing the small oil storage tank prediction frames surrounded by the large oil storage tank prediction frame from the third oil storage tank prediction frame set to obtain a final oil storage tank detection result. The application reduces the detection error rate of the oil storage tank and improves the detection precision.
Description
Technical Field
The application relates to the technical field of remote sensing image processing, in particular to a method and a device for detecting an oil storage tank based on remote sensing images.
Background
The main bodies of the detection algorithms of the current oil storage tank are divided into two categories. The first category is the traditional algorithms based on artificial features, such as: the method comprises the following steps of (1) an improved Canny edge detection and Hough transformation and rapid template matching combined algorithm, an oil tank detection algorithm based on synthetic aperture radar image shadow and bright arc, a detection algorithm based on symmetric characteristics, an algorithm based on an SVM classifier and the like; the second category is based on deep learning algorithms, such as: fast R-CNN, yoloV4 algorithm, etc. The first type of algorithm has the defects of difficult parameter setting, sensitivity to the radius, suitability for images with clear contrast and complete outlines and the like, and because factors such as shadow, textures and the like are not considered, the algorithm cannot make more accurate judgment on a circle-like building, so a large number of false detection results occur, and the detection effect is poor. The second type of algorithm improves the accuracy of detection, but to jumbo size remote sensing image, the oil storage tank belongs to the small target, is the rule for some, and is distributing in a jumble way for some, because the visible light image can receive the cloud cover influence, the background of oil tank is different, and the oil storage tank colour is different, and the probability that the false retrieval appears in the testing process is higher, can usually be with the object false retrieval of white spot form in the remote sensing image for the oil storage tank.
Disclosure of Invention
In view of the above, the present application provides a method and an apparatus for detecting an oil storage tank based on a remote sensing image, so as to solve the above technical problems.
In a first aspect, an embodiment of the present application provides a method for detecting an oil storage tank based on a remote sensing image, where the method includes:
obtaining a remote sensing image of a target area;
processing the remote sensing image by using a previously trained YOLOv5 model to obtain a first oil storage tank prediction frame set;
filtering the first oil storage tank prediction frame set by utilizing non-maximum value inhibition to obtain a second oil storage tank prediction frame set;
acquiring the width-height and the width-height ratio of each oil storage tank prediction frame in the second oil storage tank prediction frame set, and removing the oil storage tank prediction frame from the second oil storage tank prediction frame set to obtain a third oil storage tank prediction frame set when the width-height of one oil storage tank prediction frame is not up to a preset width-height threshold value or the width-height ratio is not in a preset interval;
and detecting and removing the small oil storage tank prediction frame surrounded by the large oil storage tank prediction frame from the third oil storage tank prediction frame set to obtain a final oil storage tank detection result.
Further, processing the remote sensing image by using a previously trained YOLOv5 model to obtain a first oil storage tank prediction frame set; the method comprises the following steps:
carrying out slide block slicing operation on the remote sensing image to obtain a plurality of sub-images with preset sizes;
respectively processing each sub-image by utilizing a previously trained YOLOv5 model to obtain a plurality of oil storage tank prediction frames;
and splicing the plurality of oil storage tank prediction frames of each sub-image to obtain a first oil storage tank prediction frame set.
Further, filtering the first oil storage tank prediction frame set by utilizing non-maximum suppression to obtain a second oil storage tank prediction frame set; the method comprises the following steps:
step S1: putting all oil tank prediction frames of the first oil tank prediction frame set into the set X;
step S2: sorting each oil storage tank detection frame in the set X in a descending order according to the confidence;
and step S3: acquiring an oil storage tank detection frame with the maximum confidence level in the set X, putting the oil storage tank detection frame into the set Y, and deleting the oil storage tank detection frame from the set X;
and step S4: calculating the intersection ratio of the oil storage tank detection frame with the maximum confidence coefficient and other oil storage tank detection frames of the set X one by one, and if the intersection ratio is greater than a preset threshold value, deleting the oil storage tank detection frame with the small confidence coefficient from the set X;
step S5: judging whether the set X is an empty set, if not, turning to the step S2; otherwise, go to step S6;
step S6: all the tank prediction blocks in set Y are placed into the second set of tank prediction blocks.
Furthermore, a small oil storage tank prediction frame surrounded by a large oil storage tank prediction frame is detected from the third oil storage tank prediction frame set and removed to obtain a final oil storage tank detection result; the method comprises the following steps:
sequencing the areas of all oil storage tank prediction frames of the third oil storage tank prediction frame set from large to small to obtain area [1], area [2] … area [ N ], wherein N is the number of the oil storage tank prediction frames in the third oil storage tank detection result; area [1] is the maximum value of the area of the prediction frame of the oil storage tank, and area [ N ] is the minimum value of the area of the prediction frame of the oil storage tank;
iof for calculating the ith and jth tank prediction frames (i,j) ：
Wherein i =1, … N; j =1, … N;
decision iof (i,j) If yes, obtaining a corresponding oil storage tank prediction frame with the size of i and j, and removing the oil storage tank prediction frame from the third oil storage tank prediction frame set to obtain a final oil storage tank detection result.
In a second aspect, an embodiment of the present application provides an oil storage tank detection device based on remote sensing image, the device includes:
the acquisition unit is used for acquiring a remote sensing image of a target area;
the detection unit is used for processing the remote sensing image by utilizing a previously trained YOLOv5 model to obtain a first oil storage tank prediction frame set;
the first filtering unit is used for filtering the first oil storage tank prediction frame set by utilizing non-maximum value inhibition to obtain a second oil storage tank prediction frame set;
the second filtering unit is used for acquiring the width-height and the width-height ratio of each oil storage tank prediction frame in the second oil storage tank prediction frame set, and when the width-height of one oil storage tank prediction frame is not up to a preset width-height threshold value or the width-height ratio is not in a preset interval, removing the oil storage tank prediction frame from the second oil storage tank prediction frame set to obtain a third oil storage tank prediction frame set;
and a third filtering unit for detecting and removing the small oil storage tank prediction frame surrounded by the large oil storage tank prediction frame from the third oil storage tank prediction frame set to obtain a final oil storage tank detection result.
In a third aspect, an embodiment of the present application provides an electronic device, including: the device comprises a memory, a processor and a computer program which is stored on the memory and can run on the processor, wherein the processor executes the computer program to realize the remote sensing image-based oil storage tank detection method of the embodiment of the application.
In a fourth aspect, the present application provides a computer-readable storage medium, where computer instructions are stored, and when executed by a processor, the computer instructions implement the remote sensing image-based oil tank detection method of the present application.
The application reduces the detection error rate of the oil storage tank and improves the detection precision.
Drawings
In order to more clearly illustrate the detailed description of the present application or the technical solutions in the prior art, the drawings needed to be used in the detailed description of the present application or the prior art description will be briefly introduced below, and it is obvious that the drawings in the following description are some embodiments of the present application, and other drawings can be obtained by those skilled in the art without creative efforts.
Fig. 1 is a flowchart of an oil storage tank detection method based on remote sensing images according to an embodiment of the present application;
FIG. 2 is a schematic diagram illustrating the principle of a slicing algorithm provided in an embodiment of the present application;
fig. 3 is a functional structure diagram of an apparatus for detecting an oil storage tank based on a remote sensing image according to an embodiment of the present application;
fig. 4 is a block diagram of an electronic device according to an embodiment of the present application.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present application clearer, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are some embodiments of the present application, but not all embodiments. The components of the embodiments of the present application, generally described and illustrated in the figures herein, can be arranged and designed in a wide variety of different configurations.
Thus, the following detailed description of the embodiments of the present application, presented in the accompanying drawings, is not intended to limit the scope of the claimed application, but is merely representative of selected embodiments of the application. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present application.
First, the design idea of the embodiment of the present application is briefly introduced.
In order to solve the problem that the detection accuracy rate of the existing oil storage tank detection method based on deep learning is low, the application provides the oil storage tank detection method based on the remote sensing image, the method can eliminate overlapped frames in detection frames and the detection frames which obviously do not accord with the oil tank characteristics, the false detection probability is reduced, and the accuracy rate of oil tank detection is improved.
After introducing the application scenario and the design concept of the embodiment of the present application, the following describes a technical solution provided by the embodiment of the present application.
As shown in fig. 1, an embodiment of the present application provides a method for detecting an oil storage tank based on a remote sensing image, including:
step 101: obtaining a remote sensing image of a target area;
wherein the remote sensing image is WorldView and daily drawing data, and the resolution is 0.5m and 2m;
step 102: processing the remote sensing image by using a previously trained YOLOv5 model to obtain a first oil storage tank prediction frame set;
performing sliding block operation in the large image to obtain a small-size image, traversing all slices with a certain step length according to the sequence from left to right and from top to bottom according to the slicing algorithm principle shown in FIG. 2; dividing a large image into a plurality of patch size images;
performing feature extraction by adopting a Backbone based on a Focus structure and a CSP structure, performing feature fusion by a Neck layer, and outputting the Backbone to a prediction structure for reasoning to obtain a result of a model detection small graph;
and splicing the detection results of the small images into the detection result of the large image according to the coordinates recorded by the slicing algorithm.
Step 103: filtering the first oil storage tank prediction frame set by utilizing non-maximum value inhibition to obtain a second oil storage tank prediction frame set;
specifically, the method comprises the following steps:
step S1: putting all oil tank prediction frames of the first oil tank prediction frame set into the set X;
step S2: sorting each oil storage tank detection frame in the set X in a descending order according to the confidence;
and step S3: acquiring an oil storage tank detection frame with the maximum confidence level in the set X, putting the oil storage tank detection frame into the set Y, and deleting the oil storage tank detection frame from the set X;
and step S4: calculating the intersection ratio (IOU) of the oil storage tank detection frame with the maximum confidence coefficient and other oil storage tank detection frames of the set X one by one, and if the intersection ratio is greater than a preset threshold value, deleting the oil storage tank detection frame with the small confidence coefficient from the set X;
step S5: judging whether the set X is an empty set, if not, turning to the step S2; otherwise, go to step S6;
step S6: all the tank prediction blocks in set Y are placed into a second set of tank prediction blocks.
Step 104: acquiring the width-height and the width-height ratio of each oil storage tank prediction frame in the second oil storage tank prediction frame set, and removing the oil storage tank prediction frame from the second oil storage tank prediction frame set to obtain a third oil storage tank prediction frame set when the width-height of one oil storage tank prediction frame is not up to a preset width-height threshold value or the width-height ratio is not in a preset interval;
in a relatively large-size remote sensing image, the oil storage tank belongs to a small target, but the small target also has a pixel visualization range, and the minimum width and height pixels are set to be 10 pixels. And acquiring the width and height of each prediction frame bbox in the detection result of the second oil storage tank, and comparing the width and height with the set minimum width and height, and removing the prediction frame.
Since the detection algorithm outputs a rectangular frame, and the oil storage tank belongs to a circular target, the detected target can be filtered by controlling the aspect ratio of the output rectangular frame. Setting the minimum aspect ratio to be 0.5, setting the maximum aspect ratio to be 2, and enabling the prediction frame bbox of the aspect ratio in the interval of [0.5,2] to meet the requirement, otherwise, removing the prediction frame.
Step 105: detecting and removing a small oil storage tank prediction frame surrounded by a large oil storage tank prediction frame from the third oil storage tank prediction frame set to obtain a final oil storage tank detection result;
during the detection, the detection bbox of two oil storage tanks can occur, one bbox completely surrounding the tank and the other bbox surrounding only a part of the same tank, in which case repeated bboxs are not suppressed by the IOU threshold but can be filtered out by the IOF algorithm.
In this embodiment, the step includes:
sorting the areas of all the oil storage tank prediction frames of the third oil storage tank prediction frame set from large to small to obtain area [1], area [2] … area [ N ], wherein N is the number of the oil storage tank prediction frames in the third oil storage tank detection result; area [1] is the maximum value of the area of the prediction frame of the oil storage tank, and area [ N ] is the minimum value of the area of the prediction frame of the oil storage tank;
iof for calculating the ith and jth tank prediction frames (i,j) ：
Wherein i =1, … N; j =1, … N;
decision iof (i,j) If so, acquiring a corresponding oil storage tank prediction frame with the size of i and j, and removing the oil storage tank prediction frame from the third oil storage tank prediction frame set to obtain a final oil storage tank detection result.
The mAP index is commonly used in target detection to measure the target detection accuracy. The mAP refers to the average accuracy calculated at different recall rates. Where Precision (Precision) and Recall (Recall) measure the accuracy of the algorithm.
The confusion matrix is a standard format for precision evaluation, as shown in table 1:
TABLE 1 confusion matrix
The classification standard of True and False is IOU.
The classification criteria for Positive and Negative are confidence thresholds.
Precision = TP/(TP + FP) represents the proportion of correctly predicted positive samples to the actually positive samples, and Recall = TP/(TP + FN) represents the proportion of correctly predicted positive samples to the actually positive samples.
As shown in table 2, the test results obtained by the method of the present application are the test results obtained by using only the YOLOv5 model before the treatment:
table 2: oil storage tank detection index comparison
| Image forming method | Precision | Recall | AP |
| Before treatment | 0.824 | 0.865 | 0.893 |
| After treatment | 0.924 | 0.851 | 0.899 |
It can be seen that the accuracy of the processed image is improved by approximately 10 percentage points, the recall rate is reduced by 1 percentage point, but the overall detection accuracy AP is improved, namely the accuracy of the oil storage tank detection is obviously improved.
Based on the foregoing embodiments, an embodiment of the present application provides an oil storage tank detection apparatus based on a remote sensing image, and referring to fig. 3, an oil storage tank detection apparatus 200 based on a remote sensing image provided by an embodiment of the present application at least includes:
an obtaining unit 201, configured to obtain a remote sensing image of a target area;
the detection unit 202 is configured to process the remote sensing image by using a previously trained YOLOv5 model to obtain a first oil storage tank prediction frame set;
the first filtering unit 203 is configured to filter the first oil tank prediction frame set by using non-maximum suppression to obtain a second oil tank prediction frame set;
the second filtering unit 204 is configured to obtain the width-height and the width-height ratio of each oil storage tank prediction frame in the second oil storage tank prediction frame set, and when the width-height of one oil storage tank prediction frame does not reach a preset width-height threshold or the width-height ratio is not within a preset interval, remove the oil storage tank prediction frame from the second oil storage tank prediction frame set to obtain a third oil storage tank prediction frame set;
and a third filtering unit 205 for detecting and removing the small oil tank prediction frame surrounded by the large oil tank prediction frame from the third oil tank prediction frame set to obtain a final oil tank detection result.
It should be noted that the principle of the remote-sensing-image-based oil storage tank detection apparatus 200 provided in the embodiment of the present application for solving the technical problem is similar to that of the remote-sensing-image-based oil storage tank detection method provided in the embodiment of the present application, and therefore, reference may be made to implementation of the remote-sensing-image-based oil storage tank detection apparatus 200 provided in the embodiment of the present application for implementation of the remote-sensing-image-based oil storage tank detection method provided in the embodiment of the present application, and repeated parts are not repeated.
As shown in fig. 4, an electronic device 300 provided in the embodiment of the present application at least includes: the remote sensing image-based oil storage tank detection method comprises a processor 301, a memory 302 and a computer program which is stored on the memory 302 and can run on the processor 301, wherein the processor 301 executes the computer program to realize the remote sensing image-based oil storage tank detection method provided by the embodiment of the application.
The electronic device 300 provided by the embodiment of the present application may further include a bus 303 connecting different components (including the processor 301 and the memory 302). Bus 303 represents one or more of any of several types of bus structures, including a memory bus, a peripheral bus, a local bus, and so forth.
The Memory 302 may include readable media in the form of volatile Memory, such as Random Access Memory (RAM) 3021 and/or cache Memory 3022, and may further include Read Only Memory (ROM) 3023.
The memory 302 may also include a program tool 3024 having a set (at least one) of program modules 3025, the program modules 3025 including, but not limited to: an operating subsystem, one or more application programs, other program modules, and program data, each of which, or some combination thereof, may comprise an implementation of a network environment.
Electronic device 300 may also communicate with one or more external devices 304 (e.g., keyboard, remote control, etc.), with one or more devices that enable a user to interact with electronic device 300 (e.g., cell phone, computer, etc.), and/or with any device that enables electronic device 300 to communicate with one or more other electronic devices 300 (e.g., router, modem, etc.). Such communication may be through an Input/Output (I/O) interface 305. Also, the electronic device 300 may communicate with one or more networks (e.g., a Local Area Network (LAN), a Wide Area Network (WAN), and/or a public Network, such as the internet) via the Network adapter 306. As shown in FIG. 4, the network adapter 306 communicates with the other modules of the electronic device 300 via the bus 303. It should be understood that although not shown in FIG. 4, other hardware and/or software modules may be used in conjunction with electronic device 300, including but not limited to: microcode, device drivers, redundant processors, external disk drive Arrays, disk array (RAID) subsystems, tape drives, and data backup storage subsystems, to name a few.
It should be noted that the electronic device 300 shown in fig. 4 is only an example, and should not bring any limitation to the functions and the scope of the application of the embodiments.
The embodiment of the application further provides a computer-readable storage medium, which stores computer instructions, and when the computer instructions are executed by a processor, the method for detecting an oil storage tank based on remote sensing images, provided by the embodiment of the application, is implemented.
Further, while the operations of the methods of the present application are depicted in the drawings in a particular order, this does not require or imply that these operations must be performed in this particular order, or that all of the illustrated operations must be performed, to achieve desirable results. Additionally or alternatively, certain steps may be omitted, multiple steps combined into one step execution, and/or one step broken down into multiple step executions.
While the preferred embodiments of the present application have been described, additional variations and modifications in those embodiments may occur to those skilled in the art once they learn of the basic inventive concepts. Therefore, it is intended that the appended claims be interpreted as including preferred embodiments and all alterations and modifications as fall within the scope of the application.
Finally, it should be noted that: the above embodiments are only used for illustrating the technical solutions of the present application, and not for limiting the same; although the present application has been described in detail with reference to the foregoing embodiments, it should be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some or all of the technical features may be equivalently replaced; and the modifications or the substitutions do not make the essence of the corresponding technical solutions depart from the scope of the technical solutions of the embodiments of the present application.
Claims (7)
1. A remote sensing image-based oil storage tank detection method is characterized by comprising the following steps:
obtaining a remote sensing image of a target area;
processing the remote sensing image by utilizing a previously trained YOLOv5 model to obtain a first oil storage tank prediction frame set;
filtering the first oil storage tank prediction frame set by utilizing non-maximum value inhibition to obtain a second oil storage tank prediction frame set;
acquiring the width-height and the width-height ratio of each oil storage tank prediction frame in the second oil storage tank prediction frame set, and removing the oil storage tank prediction frame from the second oil storage tank prediction frame set to obtain a third oil storage tank prediction frame set when the width-height of one oil storage tank prediction frame is not up to a preset width-height threshold value or the width-height ratio is not in a preset interval;
and detecting and removing the small oil storage tank prediction frame surrounded by the large oil storage tank prediction frame from the third oil storage tank prediction frame set to obtain a final oil storage tank detection result.
2. The remote sensing image-based oil storage tank detection method according to claim 1, characterized in that the remote sensing image is processed by using a previously trained YOLOv5 model to obtain a first oil storage tank prediction frame set; the method comprises the following steps:
carrying out slide block slicing operation on the remote sensing image to obtain a plurality of sub-images with preset sizes;
respectively processing each sub-image by utilizing a previously trained YOLOv5 model to obtain a plurality of oil storage tank prediction frames;
and splicing the plurality of oil storage tank prediction frames of each sub-image to obtain a first oil storage tank prediction frame set.
3. The remote sensing image-based oil storage tank detection method according to claim 1, characterized in that a non-maximum suppression is used for filtering the first oil storage tank prediction frame set to obtain a second oil storage tank prediction frame set; the method comprises the following steps:
step S1: putting all oil tank prediction frames of the first oil tank prediction frame set into the set X;
step S2: sorting each oil storage tank detection frame in the set X in a descending order according to the confidence;
and step S3: acquiring an oil storage tank detection frame with the maximum confidence level in the set X, putting the oil storage tank detection frame into the set Y, and deleting the oil storage tank detection frame from the set X;
and step S4: calculating the intersection ratio of the oil storage tank detection frame with the maximum confidence coefficient and other oil storage tank detection frames of the set X one by one, and if the intersection ratio is greater than a preset threshold value, deleting the oil storage tank detection frame with the small confidence coefficient from the set X;
step S5: judging whether the set X is an empty set, if not, turning to the step S2; otherwise, go to step S6;
step S6: all the tank prediction blocks in set Y are placed into the second set of tank prediction blocks.
4. The remote sensing image-based oil storage tank detection method according to claim 1, wherein a small oil storage tank prediction frame surrounded by a large oil storage tank prediction frame is detected from the third oil storage tank prediction frame set and removed to obtain a final oil storage tank detection result; the method comprises the following steps:
sequencing the areas of all oil storage tank prediction frames of the third oil storage tank prediction frame set from large to small to obtain area [1], area [2] … area [ N ], wherein N is the number of the oil storage tank prediction frames in the third oil storage tank detection result; area [1] is the maximum value of the area of the prediction frame of the oil storage tank, and area [ N ] is the minimum value of the area of the prediction frame of the oil storage tank;
iof for calculation of the ith and jth tank prediction boxes (i,j) ：
Wherein i =1, … N; j =1, … N;
judgment iof ( (i,j) If so, acquiring a corresponding oil storage tank prediction frame with the size of i and j, and removing the oil storage tank prediction frame from the third oil storage tank prediction frame set to obtain a final oil storage tank detection result.
5. The utility model provides an oil storage tank detection device based on remote sensing image, its characterized in that, the device includes:
the acquisition unit is used for acquiring a remote sensing image of a target area;
the detection unit is used for processing the remote sensing image by utilizing a previously trained YOLOv5 model to obtain a first oil storage tank prediction frame set;
the first filtering unit is used for filtering the first oil storage tank prediction frame set by utilizing non-maximum value inhibition to obtain a second oil storage tank prediction frame set;
the second filtering unit is used for acquiring the width-height and the width-height ratio of each oil storage tank prediction frame in the second oil storage tank prediction frame set, and when the width-height of one oil storage tank prediction frame is not up to a preset width-height threshold value or the width-height ratio is not in a preset interval, removing the oil storage tank prediction frame from the second oil storage tank prediction frame set to obtain a third oil storage tank prediction frame set;
and a third filtering unit for detecting and removing the small oil storage tank prediction frame surrounded by the large oil storage tank prediction frame from the third oil storage tank prediction frame set to obtain a final oil storage tank detection result.
6. An electronic device, comprising: a memory, a processor and a computer program stored on the memory and executable on the processor, the processor implementing the remote sensing image-based tank testing method according to any one of claims 1-4 when executing the computer program.
7. A computer readable storage medium storing computer instructions which, when executed by a processor, implement the remote sensing image-based tank testing method according to any one of claims 1 to 4.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211166207.7A CN115359359A (en) | 2022-09-23 | 2022-09-23 | Oil storage tank detection method and device based on remote sensing image |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211166207.7A CN115359359A (en) | 2022-09-23 | 2022-09-23 | Oil storage tank detection method and device based on remote sensing image |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115359359A true CN115359359A (en) | 2022-11-18 |
Family
ID=84006544
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211166207.7A Pending CN115359359A (en) | 2022-09-23 | 2022-09-23 | Oil storage tank detection method and device based on remote sensing image |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115359359A (en) |
-
2022
- 2022-09-23 CN CN202211166207.7A patent/CN115359359A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108229509B (en) | Method and device for identifying object class and electronic equipment | |
| CN110781885A (en) | Text detection method, device, medium and electronic equipment based on image processing | |
| CN112819821B (en) | Cell nucleus image detection method | |
| CN112989995B (en) | Text detection method and device and electronic equipment | |
| CN110619333A (en) | Text line segmentation method, text line segmentation device and electronic equipment | |
| CN111814905A (en) | Target detection method, target detection device, computer equipment and storage medium | |
| CN114240978B (en) | Cell edge segmentation method and device based on adaptive morphology | |
| CN115239644B (en) | Concrete defect identification method, device, computer equipment and storage medium | |
| CN116168351B (en) | Inspection method and device for power equipment | |
| CN116485779B (en) | Adaptive wafer defect detection method and device, electronic equipment and storage medium | |
| CN114581419A (en) | Transformer insulating sleeve defect detection method, related equipment and readable storage medium | |
| CN113870196A (en) | Image processing method, device, equipment and medium based on anchor point cutting graph | |
| CN113537037A (en) | Pavement disease identification method, system, electronic device and storage medium | |
| CN117392733A (en) | Acne grading detection method and device, electronic equipment and storage medium | |
| Haoran et al. | Egg crack detection based on support vector machine | |
| CN112001336A (en) | Pedestrian boundary crossing alarm method, device, equipment and system | |
| CN111507957A (en) | Identity card picture conversion method and device, computer equipment and storage medium | |
| CN115359359A (en) | Oil storage tank detection method and device based on remote sensing image | |
| CN115761606A (en) | Box electric energy meter identification method and device based on image processing | |
| CN114511862A (en) | Form identification method and device and electronic equipment | |
| CN115292887A (en) | Plant disease severity evaluation method and device based on lesion area ratio | |
| CN115984316B (en) | Industrial image edge extraction method and device for complex environment | |
| CN112257586B (en) | Truth box selection method, device, storage medium and equipment in target detection | |
| CN117420152B (en) | Visual inspection method, visual inspection device, computer equipment and computer readable storage medium | |
| CN112581472B (en) | Target surface defect detection method facing human-computer interaction |
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 |