Vision-based oil taking port identification method and system

Abstract

The invention provides an oil taking port recognition method and system based on vision, and the method comprises the steps: collecting an oil taking port image through a monocular camera on a mechanical arm after an oil taking robot moves to a specified oil taking position of a transformer; identifying a target area of the oil extraction port through a deep learning algorithm, extracting the target area of the oil extraction port for binarization processing, fitting the contour of the oil extraction port through a minimum enclosing rectangle, taking the central point of the minimum enclosing rectangle as the oil extraction port, and calculating the coordinate of the oil extraction port in the image; the relative distance between the tail end of the mechanical arm and the oil taking opening is measured through a laser displacement sensor; calculating the position of the oil taking port in a world coordinate system according to the coordinate of the oil taking port in the image, the relative distance from the mechanical arm to the oil taking port, the internal and external parameters of the camera and the calibration posture of the laser displacement sensor, and moving the oil taking pipe to the position of a target oil taking port by driving the mechanical arm according to the position of the oil taking port. Through the scheme, the oil extraction efficiency of the transformer can be improved, the labor cost is saved, and the safety of oil extraction operation is guaranteed.

Description

TECHNICAL FIELD

[0001] The present application belongs to the technical field of computer vision, and particularly relates to a visual-based oil taking port identification method and system. BACKGROUND

[0002] As an important device for maintaining stable operation of a power grid, a transformer may have serious accidents such as explosion and fire during operation, which endangers the safety of the power grid. In order to ensure the safe operation of the transformer, the insulating oil in the transformer is usually collected to analyze and judge the safety risk of the transformer. However, there is a certain safety risk for power grid workers to collect the insulating oil of the transformer on site.

[0003] At present, in some public robot oil taking schemes, the robot usually needs to be manually controlled to complete the oil taking operation. The specific process is as follows: after the robot drives to the target oil taking position based on automatic driving or manual control, the oil taking port position is locked through a camera, then a mechanical arm is manually controlled to approach the oil taking port, the oil taking port is automatically opened, the end of the mechanical arm approaches the oil taking port to extend a hose to complete the oil taking operation. However, due to the error of camera vision, the oil taking port position is easily identified incorrectly, which needs to be frequently manually adjusted, the actual work efficiency is low, and the labor cost is increased. SUMMARY

[0004] Therefore, the embodiments of the present application provide a visual-based oil taking port identification method and system to solve the problems of low work efficiency and increased labor cost in current transformer oil taking.

[0005] In a first aspect of the embodiments of the present application, a visual-based oil taking port identification method is provided, comprising: After the oil taking robot moves to the specified position of the transformer for oil taking, an image of the oil taking port is collected by a monocular camera on the mechanical arm; An oil taking port target area is identified through a deep learning algorithm, the oil taking port target area is extracted for binary processing, and the center point of the minimum circumscribed rectangle is taken as the oil taking port to calculate the coordinates of the oil taking port in the image; The relative distance from the end of the mechanical arm to the oil taking port is measured by a laser displacement sensor; According to the coordinates of the oil taking port in the image, the relative distance from the end of the mechanical arm to the oil taking port, the internal and external parameters of the monocular camera, and the calibrated pose of the monocular camera and the laser displacement sensor, the position of the oil taking port in the world coordinate system is calculated, and the oil taking tube is moved to the target oil taking port position by driving the mechanical arm according to the position of the oil taking port in the world coordinate system to perform the oil taking action.

[0006] In a second aspect of the embodiments of the present application, a visual-based oil taking port identification system is provided, comprising: An image data acquisition unit is configured to acquire an image of the oil extraction port through a monocular camera on the mechanical arm after the oil extraction robot moves to the designated position of the transformer oil extraction. A first coordinate calculation unit is configured to identify the target area of the oil extraction port through a deep learning algorithm, extract the target area of the oil extraction port for binary processing, and fit the contour of the oil extraction port through a minimum circumscribed rectangle, take the center point of the minimum circumscribed rectangle as the oil extraction port, and calculate the coordinates of the oil extraction port in the image. A distance data acquisition unit is configured to measure the relative distance from the end of the mechanical arm to the oil extraction port through a laser displacement sensor. A second coordinate calculation unit is configured to calculate the position of the oil extraction port in the world coordinate system according to the coordinates of the oil extraction port in the image, the relative distance from the end of the mechanical arm to the oil extraction port, the internal and external parameters of the monocular camera, and the calibrated pose of the monocular camera and the laser displacement sensor. A driving control unit is configured to move the oil extraction pipe to the target oil extraction port position through the driving of the mechanical arm according to the position of the oil extraction port in the world coordinate system, so as to perform the oil extraction action.

[0007] In a third aspect of the embodiments of the present application, a robot is provided, which includes a memory, a processor, and a computer program stored in the memory and executable by the processor, and the processor implements the steps of the method according to the first aspect of the embodiments of the present application when executing the computer program.

[0008] In a fourth aspect of the embodiments of the present application, a computer readable storage medium is provided, which stores a computer program, and the computer program is executable by a processor to implement the steps of the method according to the first aspect of the embodiments of the present application.

[0009] In the embodiments of the present application, the monocular camera and the laser displacement sensor are combined, the position of the oil extraction port in the world coordinate system is calculated according to the coordinates of the oil extraction port in the image, the relative distance from the end of the mechanical arm to the oil extraction port, and the calibration parameters, so as to realize the accurate positioning of the oil extraction port and realize the automatic oil extraction operation. This not only improves the transformer oil extraction efficiency, but also reduces the labor cost, and further ensures the safety and reliability of the transformer oil extraction operation. BRIEF DESCRIPTION OF DRAWINGS

[0010] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the following will briefly introduce the drawings needed to be used in the embodiments or prior art description. Obviously, the drawings described below are only some embodiments of the present application, and other drawings can be obtained by those skilled in the art without creative labor.

[0011] Figure 1 A flowchart of a visual-based oil extraction port identification method provided by an embodiment of the present application is shown. Figure 2 A mechanical arm schematic diagram provided for an embodiment of the present application; Figure 3 A structure schematic diagram of a visual-based oil taking port recognition system provided for an embodiment of the present application; Figure 4 A structure schematic diagram of a robot provided for an embodiment of the present application. DETAILED DESCRIPTION

[0012] In order to make the application purpose, features and advantages of the present application more obvious and easy to understand, the technical solutions in the embodiments of the present application will be described clearly and completely below with reference to the drawings in the embodiments of the present application. Obviously, the embodiments described below are only some of the embodiments of the present application, but not all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor fall within the scope of the present application.

[0013] It should be understood that the terms “comprise” and other similar expressions in the specification or claims of the present application and the above-described drawings mean covering non-exclusive inclusion, such as a process, method or system, device comprising a series of steps or units, which is not limited to the listed steps or units. In addition, “first” and “second” are used to distinguish different objects, and are not used to describe a specific order.

[0014] Please refer to Figure 1 The flowchart of a visual-based oil taking port recognition method provided by the embodiments of the present application comprises: S101, after the oil taking robot moves to the specified position of the transformer oil taking, the monocular camera on the mechanical arm collects the oil taking port image; The oil taking robot is a robot for automatically realizing navigation and oil taking, which can drive to the target oil taking position by automatic driving and complete the transformer oil taking operation. The specified position is the position of the robot completing the oil taking operation, which can be calibrated by marking the oil taking point or demarcating the oil taking area in advance.

[0015] A monocular camera is installed on the mechanical arm of the oil taking robot, as shown in Figure 2 The end of the mechanical arm is provided with an oil taking pipe, and a laser displacement sensor can be arranged below the monocular camera or at the same position.

[0016] S102, the target area of the oil taking port is recognized by a deep learning algorithm, the target area of the oil taking port is extracted for binary processing, and the contour of the oil taking port is fitted by the minimum circumscribed rectangle, the center point of the minimum circumscribed rectangle is taken as the oil taking port, and the coordinates of the oil taking port in the image are calculated; The oil outlet target area refers to an area belonging to the transformer oil outlet in the oil outlet image, and the area is composed of pixel points. After detecting the oil outlet area by the deep learning algorithm, the position of the area is indicated by a detection frame. After intercepting the oil outlet area image, binary processing is performed on the image, and the center point of the minimum circumscribed rectangle is fitted as the oil outlet position to more accurately indicate the position of the oil outlet in the image.

[0017] The deep learning algorithm is a Faster R-CNN neural network algorithm.

[0018] Optionally, the oil outlet target area image is subjected to image enhancement and noise reduction processing, and then binary processing is performed on the oil outlet target area image.

[0019] S103, measuring the relative distance from the mechanical arm end to the oil outlet by a laser displacement sensor; The laser displacement sensor is used to collect the relative distance from the mechanical arm end to the oil outlet after detecting the oil outlet in the image. Since the installation position of the laser displacement sensor on the mechanical arm is fixed and the position relative to the mechanical arm end is known, the relative distance from the displacement sensor to the oil outlet can be measured by the laser displacement sensor, and the relative distance from the mechanical arm end to the oil outlet can be calculated according to the relative position of the displacement sensor and the mechanical arm end.

[0020] S104, calculating the position of the oil outlet in the world coordinate system according to the coordinates of the oil outlet in the image, the relative distance from the mechanical arm end to the oil outlet, the internal and external parameters of the monocular camera, and the calibrated pose of the monocular camera and the laser displacement sensor, and moving the oil extraction pipe to the target oil outlet position by driving the mechanical arm according to the position of the oil outlet in the world coordinate system to perform the oil extraction action.

[0021] The conversion matrices of the image and the camera coordinates and the camera and the displacement sensor are respectively constructed, and the position of the oil outlet in the world coordinate system can be calculated in combination with the coordinates of the oil outlet in the image, the relative distance from the mechanical arm end to the oil outlet, etc. The mechanical arm end is controlled to approach the oil outlet by the motor according to the position of the oil outlet in the world coordinate system, and the oil extraction pipe is installed on the mechanical arm end. After the oil outlet is opened, the oil extraction pipe is controlled to extend to extract oil.

[0022] Optionally, the position of the mechanical arm end in the world coordinate system is calculated according to the position of the oil outlet in the world coordinate system, the relative distance from the mechanical arm end to the oil outlet, and the ranging angle of the laser displacement sensor on the mechanical arm. According to the position of the oil outlet in the world coordinate system and the position of the mechanical arm end in the world coordinate system, the relative position offset of the mechanical arm end and the oil outlet in the world coordinate system is calculated, and the oil extraction pipe of the mechanical arm end is moved to the target oil outlet position by driving the mechanical arm based on the relative position offset. Wherein, the relative distance from the end of the mechanical arm to the oil taking port is measured by the laser displacement sensor on the mechanical arm for a preset time interval, and when the relative distance is less than a predetermined value, it is determined that the oil taking tube is successfully moved to the target oil taking port position, otherwise, the position of the end of the mechanical arm in the world coordinate system is calculated according to the relative distance measured by the laser displacement sensor.

[0023] Optionally, after the oil taking action is completed, the mechanical arm is driven to move the oil taking tube out of the target oil taking port, the image of the oil taking port is collected by the monocular camera, and it is judged whether the oil taking port exists oil leakage or not by the SVM model.

[0024] After the oil taking is completed, the monocular camera collects the image of the oil taking port again to judge whether there is leakage or not, and if there is leakage, the cleaning action can be performed after the oil taking port is closed or the operator is notified.

[0025] In the embodiment, the position of the oil taking port in the world coordinate system can be accurately calculated based on the monocular camera and the laser displacement sensor, and the oil taking tube is moved to the target oil taking port position by the mechanical arm to realize automatic oil taking, which not only improves the efficiency of transformer oil taking, but also saves the labor cost and ensures the safety of transformer oil taking operation.

[0026] It should be understood that the sequence numbers of the steps in the above embodiments do not mean the order of execution, and the execution order of the processes should be determined according to their functions and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0027] Figure 3 A structure schematic diagram of an oil taking port recognition system based on vision provided by the embodiment of the present application, the system comprises: An image data acquisition unit 310 is configured to collect the image of the oil taking port by the monocular camera on the mechanical arm after the oil taking robot moves to the specified position of the transformer oil taking; A first coordinate calculation unit 320 is configured to identify the target area of the oil taking port by a deep learning algorithm, extract the target area of the oil taking port for binary processing, and fit the contour of the oil taking port by the minimum circumscribed rectangle, take the center point of the minimum circumscribed rectangle as the oil taking port, and calculate the coordinates of the oil taking port in the image. Wherein, the deep learning algorithm is a Faster R-CNN neural network algorithm.

[0028] Optionally, the oil taking port target area picture is subjected to image enhancement and noise reduction processing, and then the oil taking port target area picture is subjected to binaryzation.

[0029] A distance data acquisition unit 330 is configured to measure the relative distance from the end of the mechanical arm to the oil taking port by the laser displacement sensor. The second coordinate calculation unit 340 is used to calculate the position of the oil intake port in the world coordinate system based on the coordinates of the oil intake port in the image, the relative distance from the end of the robotic arm to the oil intake port, the intrinsic and extrinsic parameters of the monocular camera, and the calibration pose of the monocular camera and the displacement sensor. The drive control unit 350 is used to move the oil extraction pipe to the target oil extraction port position by driving the robotic arm according to the position of the oil extraction port in the world coordinate system, so as to perform the oil extraction action.

[0030] The step of moving the oil sampling pipe to the target oil sampling port position by driving the robotic arm based on the position of the oil sampling port in the world coordinate system includes: The position of the end of the robotic arm in the world coordinate system is calculated based on the position of the oil intake port in the world coordinate system, the relative distance from the end of the robotic arm to the oil intake port, and the ranging angle of the laser displacement sensor on the robotic arm. Based on the position of the oil inlet in the world coordinate system and the position of the end of the robotic arm in the world coordinate system, the relative position offset between the end of the robotic arm and the oil inlet in the world coordinate system is calculated. Based on the relative position offset, the robotic arm is driven by a motor to move the oil inlet pipe at the end of the robotic arm to the target oil inlet position. The relative distance between the end of the robotic arm and the oil intake port is measured at preset intervals using a laser displacement sensor on the robotic arm. If the relative distance is less than a predetermined value, it is determined that the oil intake pipe has successfully moved to the target oil intake port position. Otherwise, the position of the end of the robotic arm in the world coordinate system is calculated based on the relative distance measured by the laser displacement sensor.

[0031] Optionally, after the oil sampling action is completed, the robotic arm is driven to move the oil sampling tube out of the target oil sampling port, an image of the oil sampling port is acquired by a monocular camera, and an SVM model is used to determine whether there is oil leakage at the oil sampling port.

[0032] Those skilled in the art will understand that, for the sake of convenience and brevity, the specific working process of the system and modules described above can be referred to the corresponding process in the foregoing method embodiments, and will not be repeated here.

[0033] Figure 4 This is a partial structural schematic diagram of a robot according to an embodiment of the present invention. The robot is used to perform transformer oil sampling. Figure 4 As shown, the robot 4 in this embodiment includes: a memory 410, a processor 420, a system bus 430, a monocular camera 440, and a laser displacement sensor 450, etc. The memory 410 includes an executable program 4101 stored thereon. As those skilled in the art will understand, Figure 4 The robot structure shown does not constitute a limitation on the robot and may include more or fewer parts than shown, or combine certain parts, or have different arrangements of parts.

[0034] The following will be described in detail Figure 4 The various components of the robot will be described in detail: The memory 410 can be used to store software programs and modules, and the processor 420 executes various functions and data processing of the robot by running the software programs and modules stored in the memory 410. The memory 410 can mainly include a program storage area and a data storage area, wherein the program storage area can store an operating system, at least one application program required for a function (such as a sound playing function, an image playing function, etc.), etc.; and the data storage area can store data required for use of the electronic device (such as image data), etc. In addition, the memory 410 can include a high-speed random access memory, and can also include a non-volatile memory, such as at least one magnetic disk storage device, a flash memory device, or other volatile solid-state memory device.

[0035] The executable program 4101 of the transformer oil taking method is contained on the memory 410, and the executable program 4101 can be divided into one or more modules / units, which are stored in the memory 410 and executed by the processor 420 to realize transformer oil taking, etc. The one or more modules / units can be a series of computer program instruction segments capable of completing a specific function, which are used to describe the execution process of the computer program 4101 in the robot 4. For example, the computer program 4101 can be divided into functional modules such as a first coordinate calculation unit, a second coordinate calculation unit, and a drive control unit.

[0036] The processor 420 is the control center of the robot, which connects various parts of the entire robot device through various interfaces and lines, executes various functions and processes data of the robot by running or executing software programs and / or modules stored in the memory 410 and calling data stored in the memory 410, and thus monitors the overall state of the electronic device. Optionally, the processor 420 can include one or more processing units; preferably, the processor 420 can integrate an application processor and a modem processor, wherein the application processor mainly processes the operating system, application programs, etc., and the modem processor mainly processes wireless communication. It can be understood that the above-mentioned modem processor can also not be integrated into the processor 420.

[0037] The system bus 430 is used to connect the internal functional components of the computer, and can transmit data information, address information and control information. The system bus 430 can be, for example, a PCI bus, an ISA bus, a CAN bus, etc. The instructions of the processor 420 are transmitted to the memory 410 through the bus, and the memory 410 feeds back data to the processor 420. The system bus 430 is responsible for the interaction of data and instructions between the processor 420 and the memory 410. Of course, the system bus 430 can also access other devices, such as the camera 440, the laser displacement sensor 450, etc.

[0038] The monocular camera 440 is a device used to collect images of the oil extraction port, which is used to execute the instructions of the processor 420 to complete image collection and cache the images to the memory. The laser displacement sensor 450 is a device used for distance measurement, which can measure the distance between the displacement sensor and the oil extraction port according to the instructions of the processor 420. The processor calculates the relative distance from the end of the mechanical arm to the oil extraction port according to the distance data fed back by the displacement sensor.

[0039] In the embodiment of the present application, the executable program executed by the processor 420 included in the robot comprises: After the oil extraction robot moves to the designated position of the transformer oil extraction, the image of the oil extraction port is collected by the monocular camera on the mechanical arm; The target area of the oil extraction port is identified by a deep learning algorithm, the target area of the oil extraction port is extracted for binary processing, and the center point of the minimum circumscribed rectangle is taken as the oil extraction port to calculate the coordinates of the oil extraction port in the image; The relative distance from the end of the mechanical arm to the oil extraction port is measured by the laser displacement sensor; According to the coordinates of the oil extraction port in the image, the relative distance from the end of the mechanical arm to the oil extraction port, the internal and external parameters of the monocular camera, and the calibrated pose of the monocular camera and the displacement sensor, the position of the oil extraction port in the world coordinate system is calculated, and the oil extraction pipe is moved to the target oil extraction port position by driving the mechanical arm according to the position of the oil extraction port in the world coordinate system to perform the oil extraction action.

[0040] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working process of the above-described system, device and module can refer to the corresponding process in the foregoing method embodiments, which will not be described here.

[0041] In the above embodiments, the description of each embodiment has its own emphasis, and the parts not described or recorded in detail in a certain embodiment can be referred to the related description of other embodiments.

[0042] The above-described embodiments are only used to illustrate the technical solutions of the present application, and are not intended to limit the present application; although the present application has been described in detail with reference to the foregoing embodiments, it should be understood by those skilled in the art that the technical solutions recorded in the foregoing embodiments can still be modified, or some technical features can be replaced by equivalent replacements; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims

1. A visual-based oil take-out port recognition method characterized by comprising: The method comprises the steps of: After the oil-taking robot moves to the designated position of the transformer oil taking, an image of the oil taking port is collected by a monocular camera on the mechanical arm; The target area of the oil taking port is identified by a deep learning algorithm, the target area of the oil taking port is extracted for binary processing, and the center point of the minimum circumscribed rectangle is taken as the oil taking port to calculate the coordinates of the oil taking port in the image; The relative distance from the end of the mechanical arm to the oil taking port is measured by a laser displacement sensor; According to the coordinates of the oil taking port in the image, the relative distance from the end of the mechanical arm to the oil taking port, the internal and external parameters of the monocular camera, and the calibrated pose of the monocular camera and the laser displacement sensor, the position of the oil taking port in the world coordinate system is calculated, and the oil taking pipe is moved to the target oil taking port position by driving the mechanical arm according to the position of the oil taking port in the world coordinate system to perform the oil taking action.

2. The method of claim 1, wherein, The deep learning algorithm is a Faster R-CNN neural network algorithm.

3. The method of claim 1, wherein, The binary processing of the target area of the oil taking port includes: After image enhancement and noise reduction processing of the oil taking port target area picture, the oil taking port target area picture is binarized.

4. The method of claim 1, wherein, According to the position of the oil taking port in the world coordinate system, the relative distance from the end of the mechanical arm to the oil taking port, and the ranging angle of the laser displacement sensor on the mechanical arm, the position of the end of the mechanical arm in the world coordinate system is calculated. According to the position of the oil taking port in the world coordinate system and the position of the end of the mechanical arm in the world coordinate system, the relative position offset of the end of the mechanical arm and the oil taking port in the world coordinate system is calculated, and the oil taking pipe at the end of the mechanical arm is moved to the target oil taking port position by driving the mechanical arm based on the relative position offset. The relative distance from the end of the mechanical arm to the oil taking port is measured by the laser displacement sensor on the mechanical arm at intervals for a preset time, and when the relative distance is less than a predetermined value, it is determined that the oil taking pipe has successfully moved to the target oil taking port position, otherwise, the position of the end of the mechanical arm in the world coordinate system is continuously calculated according to the relative distance measured by the laser displacement sensor. The oil taking action is completed, the oil taking pipe is moved out of the target oil taking port by driving the mechanical arm, the image of the oil taking port is collected by the monocular camera, and it is judged whether the oil taking port leaks oil by the SVM model.

5. The method of claim 1, wherein, The method comprises the steps of: An image data acquisition unit is used to collect an image of the oil taking port by a monocular camera on the mechanical arm after the oil-taking robot moves to the designated position of the transformer oil taking; 6. A vision-based oil access port identification system, comprising: A first coordinate calculation unit is used to identify the target area of the oil taking port by a deep learning algorithm, extract the target area of the oil taking port for binary processing, and calculate the coordinates of the oil taking port in the image by fitting the contour of the oil taking port with the minimum circumscribed rectangle, taking the center point of the minimum circumscribed rectangle as the oil taking port; A distance data acquisition unit is used to measure the relative distance from the end of the mechanical arm to the oil taking port by a laser displacement sensor; ​ ​ A second coordinate calculation unit is configured to calculate a position of the oil extraction port in a world coordinate system according to a coordinate of the oil extraction port in the image, a relative distance from the end of the mechanical arm to the oil extraction port, internal and external parameters of the monocular camera, and a calibrated pose of the monocular camera and the laser displacement sensor. A driving control unit is configured to move the oil extraction tube to a target oil extraction port position by driving the mechanical arm according to the position of the oil extraction port in the world coordinate system, so as to perform an oil extraction action.

7. The system of claim 6, wherein, The deep learning algorithm is a Faster R-CNN neural network algorithm.

8. The system of claim 6, wherein, The moving of the oil extraction tube to the target oil extraction port position by driving the mechanical arm according to the position of the oil extraction port in the world coordinate system comprises: calculating a position of the end of the mechanical arm in the world coordinate system according to the position of the oil extraction port in the world coordinate system, the relative distance from the end of the mechanical arm to the oil extraction port, and a ranging angle of the laser displacement sensor on the mechanical arm; calculating a relative position offset between the end of the mechanical arm and the oil extraction port in the world coordinate system according to the position of the oil extraction port in the world coordinate system and the position of the end of the mechanical arm in the world coordinate system, and moving the oil extraction tube of the end of the mechanical arm to the target oil extraction port position by driving the mechanical arm based on the relative position offset; and wherein the relative distance from the end of the mechanical arm to the oil extraction port is measured by the laser displacement sensor on the mechanical arm at intervals for a preset time length, and when the relative distance is less than a predetermined value, it is determined that the oil extraction tube is successfully moved to the target oil extraction port position, otherwise, the position of the end of the mechanical arm in the world coordinate system is continuously calculated according to the relative distance measured by the laser displacement sensor.

9. A robot comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, The processor implements the steps of the visual-based oil extraction port identification method according to any one of claims 1 to 5 when executing the computer program.

10. A computer-readable storage medium storing a computer program, the computer program comprising instructions that, when executed by a computer, cause the computer to perform the method of any one of claims 1 to 9. The computer program implements the steps of the visual-based oil extraction port identification method according to any one of claims 1 to 5 when being executed.

Images