A method for detecting the cutting width of a combine harvester

Abstract

This invention relates to a method for detecting the cutting width of a combine harvester, comprising the following steps: Step S1: A laser emitted by a laser mounted on the combine harvester cyclically scans the crop in front of the cutter head; Step S2: An industrial camera mounted on the combine harvester continuously acquires images of the area in front of the cutter head; Step S3: The images acquired by the industrial camera are processed to obtain two straight lines corresponding to the cutting width edge; Step S4: The pixel distance between the two straight lines corresponding to the cutting width edge is calculated, and this pixel distance is the pixel cutting width; Step S5: The focal length and object distance of the industrial camera are obtained, and the actual cutting width is calculated based on the focal length and object distance; Step S6: The speed of the combine harvester is obtained by a Hall sensor mounted on the combine harvester, and the cutting area of ​​the combine harvester is calculated based on the obtained actual cutting width and speed. This application can quickly obtain the cutting area of ​​a combine harvester.

Description

Technical Field

[0001] This invention relates to the field of agricultural machinery technology, and specifically to a method for detecting the cutting width of a combine harvester. Background Technology

[0002] Combine harvesters play an indispensable role in modern agriculture. They not only improve agricultural production efficiency and harvest quality while reducing labor intensity and resource consumption, but also promote agricultural modernization, increase farmers' income, and foster sustainable agricultural development. Determining the cutting width of the combine harvester is crucial in agricultural production. However, because combine harvesters perform multiple tasks during operation, they generate a large amount of debris at the work site. In such harsh conditions, relying solely on human vision to judge the cutting width can lead to significant errors and make it difficult to accurately determine the grain boundaries. Therefore, real-time detection of the combine harvester's cutting width is one of the important tasks for achieving intelligent operation of combine harvesters and reducing the workload of workers.

[0003] In recent years, with the continuous development of smart agriculture, researchers both domestically and internationally have conducted numerous studies on cutting width measurement. Among these, the most prominent research direction is non-contact measurement. This method utilizes two ultrasonic sensors placed on either side of the combine harvester's header. During harvesting, the sensors emit ultrasonic signals, which are reflected back upon encountering the nearest grain. The sensors then receive these reflected signals and calculate the distance by measuring the time difference between transmission and reception. However, because crop stalks are often thin during actual planting, signals may pass through or fail to return, leading to measurement errors. Therefore, employing more precise methods to detect the harvester's cutting width in real time is crucial for achieving intelligent harvester operation and reducing the workload of workers. Summary of the Invention

[0004] In view of the shortcomings of the prior art, the purpose of this invention is to provide a method for detecting the cutting width of a combine harvester.

[0005] To achieve the above objectives, the technical solution adopted by the present invention is: a method for detecting the cutting width of a combine harvester, comprising the following steps:

[0006] Step S1: The laser emitted by the laser device set on the combine harvester is used to perform a cyclic scan of the crops in front of the header;

[0007] Step S2: Continuously acquire images of the area in front of the header using an industrial camera mounted on the combine harvester; Step S3: Process the images acquired by the industrial camera to obtain two straight lines corresponding to the edge of the cut; Step S4: Calculate the pixel distance between the two straight lines based on the obtained two straight lines corresponding to the edge of the cut, which is the pixel cut width d1.

[0008] Step S5: Obtain the focal length f and object distance D of the industrial camera. The object distance D is the distance between the installation position of the industrial camera and the center of the area scanned by the laser. Define the actual cutting width as d2. According to the principle of similar triangles, we know that: The actual cutting width is Step S6: Obtain the speed of the combine harvester using a Hall sensor installed on the combine harvester, and calculate the cutting area of ​​the combine harvester based on the actual cutting width d2 and the speed.

[0009] Furthermore, the area scanned by the laser in a cyclic pattern is a fan-shaped region, and the laser emitted by the laser is blue light.

[0010] Furthermore, in step S3, the processing of the image acquired by the industrial camera includes the following steps: denoising the image using median filtering; then, using the difference between the blue light emitted by the laser emitter and the crops and ground, performing color threshold segmentation on the image; then, extracting features from the extracted laser-irradiated area, i.e., performing edge detection; using the Canny edge detection algorithm to process the image, highlighting the actual cut edge in the laser-irradiated area of ​​the image, applying morphological processing to appropriately thicken overly thin edge lines; and finally, performing line detection, using the Hough transform line detection method to detect the two straight lines corresponding to the cut edge from the edge image.

[0011] Furthermore, the two lines are identified as the first line and the second line. Using the Hough transform line detection method, the polar coordinate parameters of the first line and the second line in the image are (ρ1, θ1) and (ρ2, θ2), respectively. The polar coordinate equations of both lines are then converted to rectangular coordinate equations. The polar coordinate equation of the first line is ρ1 = x1 cosθ1 + y1 sinθ1. Therefore, the rectangular coordinate equation of the first line is... The polar equation of the second line is ρ² = x²cosθ² + y²sinθ², then the rectangular equation of the second line is... Based on the rectangular coordinate equation of the first line, select the intercept point P1(x1,y1) of the first line in the rectangular coordinate system. Based on the rectangular coordinate equation of the second line, select the intercept point P2(x2,y2) of the second line in the rectangular coordinate system. Then, use the distance formula between two points... By calculating the distance between these two points, the pixel distance between the two lines can be obtained.

[0012] Furthermore, the intercept point P1(x1,y1) is the x-intercept point, and P2(x2,y2) is the x-intercept point.

[0013] Furthermore, the intercept point P1(x1,y1) is the y-intercept point, and P2(x2,y2) is the y-intercept point.

[0014] Furthermore, obtaining the object distance D of the industrial camera in step S5 includes the following steps: obtaining the height H1 of the industrial camera's installation position from the horizontal ground and the shortest distance H2 between the vertical plane where the industrial camera is located and the vertical plane where the laser emitted by the laser emitter hits the crop; and using the Pythagorean theorem to calculate the object distance.

[0015] In step S6, calculating the cutting area of ​​the combine harvester includes the following steps: based on the obtained vehicle speed, the distance the combine harvester travels within a certain time can be determined, and the cutting area can be obtained by multiplying the travel distance by the actual cutting width d2.

[0016] Beneficial effects: This invention employs non-contact methods, laser measurement technology, and image recognition processing technology to achieve real-time measurement of the cutting width of the harvester. Combined with Hall effect sensors to obtain the speed of the combine harvester, the cutting area of ​​the combine harvester can be obtained, reducing the burden on the driver. This invention is of great research significance for improving crop harvesting efficiency, providing relevant basis for agricultural subsidies in my country, and promoting the automation level of agricultural production in my country. Attached Figure Description

[0017] Figure 1 This is a schematic diagram of the structure of the combine harvester of the present invention;

[0018] Figure 2 This is a flowchart of the image processing of the present invention;

[0019] Figure 3 This is a schematic diagram of the object distance D of the present invention.

[0020] Reference numerals: 1. Combine harvester, 2. Laser, 3. Industrial camera, 4. Cutting table. Detailed Implementation

[0021] The present invention will now be described in further detail with reference to the accompanying drawings and specific embodiments.

[0022] This invention provides a method and device for detecting the cutting width of a combine harvester.

[0023] This invention discloses a combine harvester cutting width detection device comprising a laser 2, an industrial camera 3, a Hall sensor, an embedded processor, and a display device. The laser 2 is positioned above the header of the combine harvester. The industrial camera 3 is mounted above the header 4 of the combine harvester and above the laser 2. The industrial camera 3, the Hall sensor, and the display device are all electrically connected to the embedded processor, which is used for data processing, analysis, and storage. The Hall sensor is installed at a location that accurately measures the wheel hub speed, and a permanent magnet is mounted on the drive wheel to cooperate with the Hall sensor. The magnet should be fixed on the horizontal plane between the hydraulic motor and gear of the drive wheel to ensure that it passes through the Hall element when the drive wheel rotates. The Hall sensor is connected to a data acquisition card to ensure stable data transmission. A data acquisition card suitable for vehicle speed measurement is selected, and a wireless signal transmitter is installed and connected to the data acquisition card to transmit the acquired vehicle speed data to the embedded processor. The embedded processor is connected to the industrial camera 3 via Ethernet. The embedded processor can also be connected to a touch-screen LCD.

[0024] Laser 2 uses a line scanning method to cyclically detect objects within a fan-shaped area. Scanning is performed using a mechanical rotating platform. Laser 2 is mounted on a rotating platform, and the platform is driven to rotate by a motor to achieve scanning. The motor shaft is directly connected to the rotating platform; when the motor rotates, it drives the platform and the laser 2 mounted on it to rotate together. The speed and range of the laser scan can be adjusted by controlling the motor's rotation speed and rotation angle.

[0025] An embodiment of the present invention provides a method for detecting the cutting width of a combine harvester, which uses the above-mentioned detection device for detection and includes the following steps:

[0026] Step S1: The laser 2 installed on the combine harvester 1 emits a laser to scan the crops in front of the header 4 in a cyclic manner;

[0027] Step S2: Obtain an image of the area in front of the header 4 using an industrial camera 3 mounted on the combine harvester 1; Step S3: Process the image obtained by the industrial camera 3 to obtain two straight lines corresponding to the edge of the cut; Step S4: Calculate the pixel distance between the two straight lines based on the obtained two straight lines corresponding to the edge of the cut, which is the pixel cut width d1.

[0028] Step S5: Obtain the focal length f and object distance D of the industrial camera 3. The object distance D is the distance between the mounting position of the industrial camera 3 and the center of the area scanned by the laser 2. Define the actual cutting width as d2. According to the principle of similar triangles, we know that: The actual cutting width is Step S6: Obtain the speed of combine harvester 1 using a Hall sensor installed on combine harvester 1, and calculate the cutting area of ​​combine harvester 1 based on the actual cutting width d2 and the speed.

[0029] In step S1, the area scanned cyclically by laser 2 is a fan-shaped region. The orthographic projection of the header 4 falls within this fan-shaped region, and the laser emitted by laser 2 is blue light. Laser 2 emits laser light towards the crop in front of the header 4 of the combine harvester 1.

[0030] In step S3, the image acquired from industrial camera 3 is transmitted to the embedded processor for further processing. The processing of the image acquired by industrial camera 3 includes the following steps: noise reduction is performed using median filtering; then, color thresholding is performed on the image based on the difference between the blue light emitted by the laser emitter and the crops and ground; feature extraction, i.e., edge detection, is performed on the extracted laser-irradiated area using the Canny edge detection algorithm to highlight the actual edge portion of the laser-irradiated area. The Canny operator first smooths the image using Gaussian filtering to reduce noise, then calculates the gradient magnitude and direction of the image, and accurately detects the edge of the laser-irradiated area through steps such as non-maximum suppression and double threshold detection. After detecting the edge of the laser-irradiated area, since the laser emission is fan-shaped, its edge portion appears as a straight line segment in the image. Then, morphological processing is performed, using dilation to appropriately thicken overly thin edge lines, making them more stable and less prone to breakage or loss in subsequent processing, thus better serving subsequent line detection and width calculation operations. Subsequently, line detection is performed using the Hough transform line detection method to detect the two straight lines corresponding to the cut edge from the edge image. Specifically, the Hough transform line detection method is used to detect the straight lines representing the edge of the laser-irradiated area from the edge image, finding the dividing point between the crop and the ground, thus obtaining the dividing lines, i.e., the lines corresponding to the cut edge. Median filtering is used for noise reduction to smooth the image, preserving edge details and facilitating accurate extraction of the laser-irradiated area and related features.

[0031] The laser emitter emits blue light, creating specific blue areas in the image. Color thresholding can be used to extract pixels within a specific blue color range; these pixels represent the areas illuminated by the laser. In the RGB color space, the blue channel has relatively high values. A threshold range for the blue channel can be set to extract the laser-illuminated areas. For example, in an 8-bit image (channel value range 0-255), if the blue channel value is greater than 180, while the red and green channel values ​​are relatively low (e.g., less than 80), then that pixel is considered to belong to the laser-illuminated area.

[0032] Specifically, two straight lines are defined as the first line and the second line. Using the Hough transform line detection method, the polar coordinate parameters of the first line and the second line in the image are detected as (ρ1, θ1) and (ρ2, θ2), respectively. The polar coordinate equations of both lines are then converted to rectangular coordinate equations. The polar coordinate equation of the first line is ρ1 = x1 cosθ1 + y1 sinθ1. Therefore, the rectangular coordinate equation of the first line is... The polar equation of the second line is ρ² = x²cosθ² + y²sinθ², then the rectangular equation of the second line is... Based on the rectangular coordinate equation of the first line, select the intercept point P1(x1,y1) of the first line in the rectangular coordinate system. Based on the rectangular coordinate equation of the second line, select the intercept point P2(x2,y2) of the second line in the rectangular coordinate system. Then, use the distance formula between two points... By calculating the distance between these two points, the pixel distance between the two lines can be obtained.

[0033] In this implementation, the intercept point P1(x1,y1) is the x-intercept point, which is the coordinate of the intersection of the rectangular coordinate equation of the first line and the X-axis in the rectangular coordinate system. P2(x2,y2) is the x-intercept point, which is the coordinate of the intersection of the rectangular coordinate equation of the second line and the X-axis in the rectangular coordinate system.

[0034] In step S5, the focal length f of the industrial camera 3 is obtained using a checkerboard calibration board. The checkerboard is placed within the camera's field of view, and multiple images are captured from different angles and positions. Using the pixel coordinates of the checkerboard corner points in the images, the focal length f of the industrial camera 3 can be calculated using a specific algorithm (such as the Zhang Zhengyou calibration method).

[0035] Step S5, obtaining the object distance D of the industrial camera 3, includes the following steps: obtaining the height H1 of the installation position of the industrial camera 3 from the horizontal ground and the shortest distance H2 between the vertical plane of the industrial camera 3 and the vertical plane of the laser emitted by the laser on the crop; and using the Pythagorean theorem to calculate the object distance.

[0036] In step S6, calculating the cutting area of ​​combine harvester 1 includes the following steps: based on the obtained vehicle speed, the moving distance of combine harvester 1 within a certain time can be obtained, and the cutting area can be obtained by multiplying the moving distance by the actual cutting width d2.

[0037] Of course, the present invention is not limited to the embodiments described above. Several other embodiments based on the design concept of the present invention are also provided below.

[0038] For example, in other embodiments, unlike the embodiments described above, the intercept point P1(x1,y1) can also be the y-intercept point, that is, the coordinates of the first straight line's rectangular coordinate equation at the intersection of the rectangular coordinate system and the Y-axis, and P2(x2,y2) can also be the y-intercept point, that is, the coordinates of the first straight line's rectangular coordinate equation at the intersection of the rectangular coordinate system and the Y-axis.

[0039] The above description is merely a preferred embodiment of the present invention and is not intended to limit the present invention in any way. Although the present invention has been disclosed above with reference to preferred embodiments, it is not intended to limit the present invention. Any person skilled in the art can make some modifications or alterations to the above-disclosed technical content to create equivalent embodiments without departing from the scope of the present invention. Any simple modifications, equivalent changes, and alterations made to the above embodiments based on the technical essence of the present invention without departing from the scope of the present invention shall still fall within the scope of the present invention.

Claims

1. A method for detecting the cutting width of a combine harvester, characterized in that, Includes the following steps: Step S1: The laser emitted by the laser device set on the combine harvester is used to perform a cyclic scan of the crops in front of the header; Step S2: Continuously acquire images of the area in front of the header using an industrial camera mounted on the combine harvester; Step S3: Process the image acquired by the industrial camera to obtain two straight lines corresponding to the edge of the cut; Step S4: Based on the two straight lines corresponding to the obtained cut edge, calculate the pixel distance between the two straight lines. This pixel distance is the pixel cut width d1. Step S5: Obtain the focal length f and object distance D of the industrial camera. The object distance D is the distance between the installation position of the industrial camera and the center of the area scanned by the laser. Define the actual cutting width as d2. According to the principle of similar triangles, we know that: The actual cutting width is Step S6: Obtain the speed of the combine harvester using a Hall sensor installed on the combine harvester, and calculate the cutting area of ​​the combine harvester based on the actual cutting width d2 and the speed.

2. The method for detecting the cutting width of a combine harvester according to claim 1, characterized in that, The area scanned by the laser in a cyclic pattern is a fan-shaped region, and the laser emitted by the laser is blue light.

3. The method for detecting the cutting width of a combine harvester according to claim 2, characterized in that, In step S3, the processing of the image acquired by the industrial camera includes the following steps: denoising the image using median filtering; then, using the difference between the blue light emitted by the laser emitter and the crops and ground, performing color thresholding on the image; then, extracting features from the extracted laser-irradiated area, i.e., performing edge detection; using the Canny edge detection algorithm to process the image, highlighting the edges of the cutting platform and the actual cutting width in the laser-irradiated area of ​​the image, applying morphological processing to appropriately thicken overly thin edge lines; and finally, performing line detection, using the Hough transform line detection method to detect the two straight lines corresponding to the cutting width edges from the edge image.

4. The method for detecting the cutting width of a combine harvester according to claim 1, characterized in that, Two straight lines are identified as the first line and the second line. Using the Hough transform line detection method, the polar coordinates of the first and second lines in the image are (ρ1, θ1) and (ρ2, θ2), respectively. The polar equations of both lines are then converted to rectangular coordinates. The polar equation of the first line is ρ1 = x1 cosθ1 + y1 sinθ1. Therefore, the rectangular equation of the first line is... The polar equation of the second line is ρ² = x²cosθ² + y²sinθ², then the rectangular equation of the second line is... Based on the rectangular coordinate equation of the first line, select the intercept point P1(x1,y1) of the first line in the rectangular coordinate system. Based on the rectangular coordinate equation of the second line, select the intercept point P2(x2,y2) of the second line in the rectangular coordinate system. Then, use the distance formula between two points... By calculating the distance between these two points, the pixel distance between the two lines can be obtained.

5. The method for detecting the cutting width of a combine harvester according to claim 4, characterized in that, The intercept point P1(x1,y1) is the x-intercept point, and P2(x2,y2) is the x-intercept point.

6. The method for detecting the cutting width of a combine harvester according to claim 4, characterized in that, The intercept point P1(x1,y1) is the y-intercept point, and P2(x2,y2) is the y-intercept point.

7. The method for detecting the cutting width of a combine harvester according to claim 1, characterized in that, Step S5, obtaining the object distance D of the industrial camera, includes the following steps: obtaining the height H1 of the industrial camera's installation position above the horizontal ground and the shortest distance H2 between the vertical plane of the industrial camera and the vertical plane of the laser emitted by the laser on the crop; and using the Pythagorean theorem to calculate the object distance.

8. The method for detecting the cutting width of a combine harvester according to claim 1, characterized in that, In step S6, calculating the cutting area of ​​the combine harvester includes the following steps: based on the obtained vehicle speed, the distance the combine harvester travels within a certain time can be determined, and the cutting area can be obtained by multiplying the travel distance by the actual cutting width d2.

Images