Crop Row Navigation Line Detection Using Regional Integral Difference
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing methods for detecting field navigation lines in agricultural fields, particularly for crops like corn and sugarcanes in their late growth stage, fail due to overlapping branches and leaves, making it difficult to extract navigation information effectively.
Innovation Solution
A method utilizing regional integral difference and color space transformation to detect crop rows, involving image acquisition, binarization, longitudinal integration, neighborhood setting, and univariate regression models to determine crop row centerlines, which improves adaptability and accuracy in navigating closed crop rows.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If traditional methods (Hough transform, template matching, linear regression) are used to detect crop rows, then navigation information can be extracted for crops with larger spacing, but these methods fail when crop rows are closed (overlapping branches and leaves in late growth stage)
Solution Approach 1:
The patent transforms the detection parameter from individual crop row features to regional integral differences. By calculating the integral of pixel values in different regions and comparing differences between adjacent regions, the method detects navigation lines based on overall regional characteristics rather than individual crop features, making it effective for closed crop rows where individual rows are no longer distinguishable
Solution Approach 2:
The patent transitions from one-dimensional crop row detection to two-dimensional regional integration. Instead of detecting lines along the crop row direction, it integrates pixel values over rectangular regions and detects navigation lines based on differential integration results, adding a spatial dimension to the detection approach
2Reliability
If regional integral difference method is used to detect closed crop rows, then navigation information extraction becomes effective, but the method requires complex image processing steps including color space transformation, binarization, longitudinal integration, and neighborhood operations
Solution Approach 1:
The patent divides the image processing into distinct sequential stages: color space transformation to HSI, binarization based on hue thresholds, longitudinal integration to accumulate pixel values vertically, neighborhood operations to calculate regional differences, and final navigation line extraction. This segmentation makes the complex process manageable and systematically implementable
Solution Approach 2:
The patent introduces intermediate representations at each processing stage: HSI color space as an intermediary for color analysis, binary images as intermediaries for feature extraction, longitudinal integral images as intermediaries for regional comparison, and neighborhood difference maps as intermediaries for navigation line detection. These intermediaries facilitate the transformation from raw image to navigation information
3Ease of operation
If satellite positioning system is used for field navigation, then navigation control can be implemented for determined walking paths, but it cannot adapt to changing crop types and growth conditions that require path adjustment
Solution Approach 1:
The patent implements a feedback mechanism where the navigation system continuously detects crop row positions and navigation line deviations using image processing, then uses this information to adjust and correct the machinery's walking path in real-time. This closed-loop feedback enables adaptation to changing field conditions while maintaining navigation control
Solution Approach 2:
The system enables the agricultural machinery to autonomously detect its own position relative to crop rows and automatically adjust its path without external intervention. The navigation system serves itself by using onboard cameras and processors to continuously monitor and correct its own operation based on detected field conditions
Data Source
AI summary
A method for detecting a field navigation line after ridge sealing of crops includes the following steps. A field crop image is acquired. Image color space transformation, image binaryzation, longitudinal integration, neighborhood setting and region integration calculation are sequentially performed on the field crop image to obtain a crop row image. Detections of an initial middle ridge, a left ridge and a right ridge are performed on the crop row image to obtain center lines of the initial middle ridge, left ridge and right ridge. Center lines of a left (right) crop row are established by using an area 1 between the center lines of the left (right) ridge and the initial middle ridge. A center line model of a middle ridge is established by using an area 0 between the center lines of the left and right crop rows, namely a navigation line of a field operation machine.