Detection of Corn Plant Population and Row Spacing Using Computer Vision

In this paper we present a new vision-based method to measure corn plant spacing and population at early growth stage. Images were acquired from a top-mounted camera under dayLight condition. Algorithms were developed to mosaic image sequence, vegetation segmentation, image thinning, stem center identification, row Line fitting, plant count and plant spacing measurement. Compared the results of vision-based system with manual stand counts in 3 varieties with 10 repetitions of 10 m sections of corn rows. Our system was well correlated to mannual stand count, and corn plant spacing estimation had no significant difference with manual stand measurements.