Abstract

Detection of weeds and crops is the key step for precision spraying using the spraying herbicide robot and precise fertilization for the agriculture machine in the field. On the basis of k-mean clustering image segmentation using color information and connected region analysis, a method combining multi feature fusion and support vector machine (SVM) was proposed to identify and detect the position of corn seedlings and weeds, to reduce the harm of weeds on corn growth, and to achieve accurate fertilization, thereby realizing precise weeding or fertilizing. First, the image dataset for weed and corn seedling classification in the corn seedling stage was established. Second, many different features of corn seedlings and weeds were extracted, and dimensionality was reduced by principal component analysis, including the histogram of oriented gradient feature, rotation invariant local binary pattern (LBP) feature, Hu invariant moment feature, Gabor feature, gray level co-occurrence matrix, and gray level-gradient co-occurrence matrix. Then, the classifier training based on SVM was conducted to obtain the recognition model for corn seedlings and weeds. The comprehensive recognition performance of single feature or different fusion strategies for six features is compared and analyzed, and the optimal feature fusion strategy is obtained. Finally, by utilizing the actual corn seedling field images, the proposed weed and corn seedling detection method effect was tested. LAB color space and K-means clustering were used to achieve image segmentation. Connected component analysis was adopted to remove small objects. The previously trained recognition model was utilized to identify and label each connected region to identify and detect weeds and corn seedlings. The experimental results showed that the fusion feature combination of rotation invariant LBP feature and gray level-gradient co-occurrence matrix based on SVM classifier obtained the highest classification accuracy and accurately detected all kinds of weeds and corn seedlings. It provided information on weed and crop positions to the spraying herbicide robot for accurate spraying or to the precise fertilization machine for accurate fertilizing.

Highlights

  • Principal component analysis (PCA) was used to reduce the dimension of features with more dimensions, and some new information was extracted from the original data, which reduced the number of variables and attained the main contradiction

  • In addition to the gray information of gray level-gradient co-occurrence matrix (GGCM) was proposed on the basis of gray level co-occurrence matrix (GLCM)

  • 18 kinds of fusion strategies features were used besides the 6 single features, including histogram of oriented gradient (HOG), rotation-invariant local binary pattern (LBP), Hu invariant moments, Gabor, GLCM, and GGCM

Read more

Summary

Introduction

Comprehensive experiments of weed detection were conducted under the conditions of HOG, rotation invariant LBP, Hu invariant moment, Gabor, GGCM, GLCM, and their different feature fusion strategies These six features are the most commonly used feature descriptors in plant leaf recognition in recent years. A feature fusion scheme with relatively high classification accuracy was proposed, and the position detection of corn seedlings and weeds was achieved based on k-mean clustering image segmentation using color information and connected region analysis and SVM classifier, which provided location information to the spraying pesticide robot for the accurate spraying of weeds or to the precise fertilizer machine in later stages

Basic Idea of Experiment
Dataset Establishment and Preprocessing
Feature
Feature Extraction of Crops and Weeds
HOG Features
Hu Moment Invariants Features
Rotation Invariant LBP Features
Gabor Features
Gray Level Co-Occurrence Matrix Features
Gray Level-Gradient Co-Occurrence Matrix Features
Training
Test of Actual Field Dataset at Corn Seedling Stage
Experiment on Leaves DataSet
Actual Field Image Test
12. Experimental
Conclusions
Full Text
Published version (Free)

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call