Machine-vision weed density estimation for real-time, outdoor lighting conditions

A system to estimate the weed density between two rows of soybeans was deve loped. An environmentally adaptive segmentation algorithm (EASA) was used t o segment the plants from the background of the image. The effect of two im age data transformations on the segmentation performance of the EASA was in vestigated, and the RGB-IV1V2 transformation resulted in significantly high er quality segmentation results based on morphological opening and closing pixel loss over the RGB-rgb transformation. An adaptive scanning algorithm (ASA) was developed and used to automatically detect crop inter-row edges a nd to estimate the number of weeds in the inter-row area. Two sets of image s were acquired under sunny and overcast sky conditions. The ASA-detected c rop row edge positions were significantly correlated with the manually dete cted crop row positions, with the distribution skewed towards positions int ernal to the row. ASA weed density estimates were highly correlated with ma nual weed counts for both lighting conditions. However; when a limited rang e of the data was considered, much lower correlations resulted, revealing a loss of spatial color resolution due to the transmission of the video sign al. The mean execution time of the ASA was 0.038 s for 0.91 m (3 ft) long i nter-row regions showing that the algorithm met the real-time constraints n ecessary to be used as a sensing system for a variable-rate herbicide appli cator.