Image Segmentation between Crop and Weed using Hyperspectral Imaging for Weed Detection in Soybean Field

The goal of this study was image segmentation between crop and weed using hyperspectral imaging for weed detection. This technique is useful for selective weeding using spot spraying or a robotic system. A hyperspectral image consists of a large number of pixel spectra. Therefore, image segmentation was executed pixel by pixel. After each pixel spectrum was extracted from the image, it was identified as soil or plant. If the pixel spectrum was identified as plant, it was categorized as crop or weed. For the pixel discriminant model between soil and plant, simple NDVI thresholding was employed. The pixel discriminant model between crop and weed consisted of normalization, generation of explanatory variables and discrimination, and four types of models were developed and validated. Finally, segmented images between crop and weed were generated from the hyperspectral images by applying these models. As the validation results, pixel discrimination between soil and plant was performed with 99.9%. Also, most pixel discriminant models between crop and weed had a success rate of more than 90%. As a result of image segmentation between crop and weed, most hyperspectral images were segmented correctly. This study demonstrated the possibility of weed detection using hyperspectral imaging.

[1]  Lei Tian,et al.  CLASSIFICATION OF BROADLEAF AND GRASS WEEDS USING GABOR WAVELETS AND AN ARTIFICIAL NEURAL NETWORK , 2003 .

[2]  Brian D. Ripley,et al.  Pattern Recognition and Neural Networks , 1996 .

[3]  Lei Tian,et al.  Machine-vision weed density estimation for real-time, outdoor lighting conditions , 1999 .

[4]  Chun-Chieh Yang,et al.  Development of neural networks for weed recognition in corn fields , 2002 .

[5]  Hiroshi Okamoto,et al.  Distinction between Sugar Beet and Weeds for Development of Automatic Thinner and Weeding Machine of Sugar Beet , 2002 .

[6]  Hiroshi Okamoto,et al.  Object-oriented software framework development for agricultural hyperspectral imaging analysis , 2006 .

[7]  Lei Tian,et al.  AERIAL CIR REMOTE SENSING FOR WEED DENSITY MAPPING IN A SOYBEAN FIELD , 2001 .

[8]  Hiroshi Okamoto,et al.  Plant classification for weed detection using hyperspectral imaging with wavelet analysis , 2007 .

[9]  Chun-Chieh Yang,et al.  DIFFERENTIATION OF CROP AND WEEDS BY DECISION-TREE ANALYSIS OF MULTI-SPECTRAL DATA , 2004 .

[10]  Shiv O. Prasher,et al.  HYPERSPECTRAL IMAGE CLASSIFICATION TO DETECT WEED INFESTATIONS AND NITROGEN STATUS IN CORN , 2003 .

[11]  P. Dutilleul,et al.  CLASSIFICATION ACCURACY OF DISCRIMINANT ANALYSIS, ARTIFICIAL NEURAL NETWORKS, AND DECISION TREES FOR WEED AND NITROGEN STRESS DETECTION IN CORN , 2005 .

[12]  Kenshi Sakai,et al.  Development of Remote Sensing Software Based on Hyperspectral Imaging Framework , 2006 .