An FPGA-based smart camera for accurate chlorophyll estimations

In this work, a new chlorophyll estimation approach based on the reflectance/transmittance from the leaf being analyzed is proposed. First, top/underside images from the leaf under analysis are captured, then, the base parameters (reflectance/transmittance) are extracted. Finally, a double-variable linear regression model estimates the chlorophyll content. To estimate the base parameters, a novel optical arrangement is presented. On the other hand, in order to provide a portable device suitable for chlorophyll estimation under large scale food crops, we have implemented our optical arrangement and our algorithmic formulation inside an field-programmable gate array (FPGA)-based smart camera fabric. Experimental results demonstrated that the proposed approach outperforms (in terms of accuracy and processing speed) most previous vision-based approaches, reaching more than 97% accuracy and delivering fast chlorophyll estimations (near 5 ms per estimation).