Dr. Pankaj GuptaLadani Uttam Rameshbhai2020-07-062020-07-062018http://krishikosh.egranth.ac.in/handle/1/5810148651Efficient weed management is necessary is one way to increase productivity with judicious use of inputs. To distinguish between weeds and crops difference between spectral characteristics of plants in the visible and near-infrared (NIR) wavebands and the Normalized Difference Vegetation Index (NDVI) is being used. Thus, to precisely manage the weeds a spray unit for herbicide application in combination with NDVI based sensing unit for plant and weed discrimination was developed. To accomplish this, two laser line diodes of 650 nm from red band and 780 nm from infrared band, were used to sequentially illuminate the target area. The reflected light was collected by the Si photo diode and send to Arduino UNO, a widely used open-source microcontroller board based on the ATmega328P microcontroller. Programming was done in arduino software (IDE) in C++ language for signal conditioning and processing to discriminate the weed from plant and soil. After detection of weed, the solenoid valve was actuated to operate the spray unit consisting of an existing battery operated knapsack type sprayer with a lance.en-USnullThesis