Skip to main content
ARS Home » Southeast Area » Stoneville, Mississippi » Crop Production Systems Research » Research » Publications at this Location » Publication #322957
Title: Identification of seedling cabbages and weeds using hyperspectral imaging

Author
item DENG, WEI - National Engineering Research Center For Information Technology In Agriculture
item Huang, Yanbo
item ZHAO, CHUNJIANG - National Engineering Research Center For Information Technology In Agriculture
item WANG, XIU - National Engineering Research Center For Information Technology In Agriculture

Submitted to: International Journal of Agricultural and Biological Engineering
Publication Type: Peer Reviewed Journal
Publication Acceptance Date: 10/25/2015
Publication Date: 10/30/2015
Citation: Deng, W., Huang, Y., Zhao, C., Wang, X. 2015. Identification of seedling cabbages and weeds using hyperspectral imaging. International Journal of Agricultural and Biological Engineering. 8(5):65-72.

Interpretive Summary: Target detection and location in pest management are critical for site-specific chemical application over crop fields. Traditional detection and location methods are time-consuming and laborious. A cost-effective method is needed to rapidly identify weeds in the fields of cabbage. Scientists in National Research Center of Intelligent Equipment for Agriculture in Beijing, China and USDA-ARS Crop Production Systems Research Unit, Stoneville, Mississippi, collaboratively developed a hyperspectral imaging method to identify seedling cabbages from weeds. Results indicated that the classification model we determined was able to completely distinguish weeds from cabbages and soil background. The success of this development can provide accurate information for spray systems to be activated at right time and location on the targets for precision weed management in cabbage farming. The system can provide in field guidance to pesticide applicators and research will be beneficial to cabbage and other vegetable farmers.

Technical Abstract: Target detectionis one of research focues for precision chemical application. This study developed a method to identify seedling cabbages and weeds using hyperspectral spectral imaging. In processing the image data, with ENVI software, after dimension reduction, noise reduction, de-correlation for high-dimensional data, and selection of the region of interest, the SAM (Spectral Angle Mapping) model was built for automatic identification of cabbages and weeds. With the HSI (HyperSpectral Imaging) Analyzer, the training pixels were used to calculate the average spectrum as the standard spectrum and the parameters of the SAM model which had the best classification results with 3-point smoothing. The zero-order derivative and 6-degrees spectral angle was determined to achieve the accurate identification of the background, weeds, and cabbages. In comparison, the SAM model can completely separate the plants from the soil background but not perfect for weeds to be separated from the cabbages. In conclusion, the SAM classification model with the HSI analyzer could completely distinguished weeds from background and cabbages.