Tractor rotary cultivation visual navigation method on basis of new and old soil boundary lines
A visual navigation and tractor technology, applied in the field of agricultural engineering, can solve the problems of high cost, satellite navigation signal interruption and delay, difficult navigation, etc., and achieve the effect of high precision and short time consumption
Inactive Publication Date: 2018-04-24
NANJING AGRICULTURAL UNIVERSITY
View PDF0 Cites 2 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Both GPS and Beidou technology need to use ground-based enhanced differential technology, which is costly, and due to factors such as geographical location and meteorological environment, satellite navigation signals in farmland are sometimes interrupted and delayed
Visual navigation technology is widely used, but at present, the automatic navigation technology of agricultural machinery based on machine vision mostly extracts the navigation line by studying the distribution pattern of crop rows, while the field crops have been harvested during the rotary tillage operation of agricultural machinery, it is difficult to navigate based on crop rows
Method used
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
Embodiment 1
[0042] Such as figure 1 As shown, a visual navigation method for tractor rotary farming based on the boundary line of new and old soil, which is implemented according to the following steps:
[0043] Step 1: collect the visual image p(x, y) in front of the tractor through the camera;
[0044] Step 2: Grayscale the image by the formula f(x, y)=(R(x, y)+G(x, y)+B(x, y)) / 3, and convert to YCrCb color space, Where Y=0.299*R+0.587*G+0.114*B, Cr=(R-Y)*0.713+128, Cb=(B-Y)*0.564+128;
[0045] Step 3: Carry out guide filter processing to image under YCrCb color space;
[0046] Such as figure 2 As shown, the processing of guided filtering, that is, the working process of solving the "local linear model" is:
[0047] Let q be the value of the output pixel; i and k are the pixel indices; I is the value of the input image, i.e. the image to be filtered or the guide image of other images; a and b are the coefficients of the linear function when the window center is at k; p is the imag...
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More PUM
Login to View More Abstract
The invention provides a tractor rotary cultivation visual navigation method on the basis of new and old soil boundary lines. The tractor rotary cultivation visual navigation method on the basis of Guided Image Filter and Shearlet Transform is used for extracting the new and old soil boundary lines to complete tractor visual navigation for characteristics of diversification of crop rows and unevenillumination in working environments when rotary cultivation operation is carried out by tractors. The tractor rotary cultivation visual navigation method includes quickly converting images into YCrCb color spaces and carrying out guided image filter on grayed images; extracting edge information of new and old soil by the aid of Shearlet-canny operators; carrying out Hough transform to obtain visual navigation lines. The tractor rotary cultivation visual navigation method on the basis of the new and oil soil boundary lines has the advantage that the tractor rotary cultivation visual navigation method can be used for intelligent navigation in farmland environments.
Description
technical field [0001] The invention relates to an intelligent tractor visual navigation method, in particular to a tractor-based field operation visual navigation method for new and old soil boundary lines, and belongs to the technical field of agricultural engineering. Background technique [0002] In the context of the rapid development of agricultural mechanization and intelligent technology, precision agriculture has made great progress, especially the automatic navigation technology of intelligent tractors. Under the conditions of farmland operations such as diverse crop rows and uneven lighting, automatic visual navigation technology provides a good solution to the constraints of the existing technological development level. There are mainly two existing automatic navigation methods, one is centimeter-level satellite precise navigation (GPS, Beidou) that can realize farmland, and the other is visual navigation with complex algorithms but low cost. Both GPS and Beidou...
Claims
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More Application Information
Patent Timeline
Login to View More Patent Type & Authority Applications(China)
IPC IPC(8): G01C21/20
CPCG01C21/20
Inventor 卢伟陈益杉王家鹏王新宇
Owner NANJING AGRICULTURAL UNIVERSITY