An FPGA‐based smart camera for accurate chlorophyll estimations

Abstract

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).

Developing a Modern Greenhouse Scientific Research Facility—A Case Study

“…A hyperspectral and spectroscopy system camera is used [34,35] to obtain better results. There is also an example of a custom-made system used in [36]. The camera can observe the plant as a whole or just a part of it, such as the leaves.…”

Guest editorial: Special issue on computational image sensors and smart camera hardware

“…The article “An FPGA‐Based Smart Camera for Accurate Chlorophyll Estimations” by Pérez‐Patricio et al describes an embedded vision system tailored for a particular application: analysis of reflectance/transmittance of tree leaves for precision agriculture. This smart camera can estimate chlorophyll content at about 200 fps with 97% accuracy, outperforming most previous approaches.…”