Title: Precision agriculture – three big challenges with many imaging solutions?
Speaker: Prof. Jan van Aardt (Rochester Institute of Technology, Chester F. Carlson Center for Imaging Science)
Time: Dec 17, 2024, at 10 am (EST New York time) (UTC time: 3:00 PM, Dec 17 2024; Beijing time: 11:00 PM, Tuesday, December 17, 2024; Paris time: 17 December 2024 at 4:00 pm). See the conversion to other time zones using this time zone announcement.
**Please click this URL to start or join:https://adelaide.zoom.us/j/81925028718?pwd=LodZ8cvUqkjSyIiDa5umGlVnQCAS6N.1&from=addon Password: 857435
Zoom Meeting ID: 819 2502 8718 Password: 857435**
Abstract. Relatively recent advances in unmanned aerial systems (UAS), or drone technology, as well as miniaturization of complex remote sensing systems, have enabled novel approaches to precision agriculture. Specifically, imaging spectroscopy (hyperspectral) and light detection and ranging (lidar) can be used for three key agricultural management needs, namely disease detection, yield prediction, and harvest scheduling. This talk will focus on efforts by RIT and collaborator Cornell University to develop robust analytical approaches to a range of precision agriculture challenges. We will highlight efforts to develop risk models for proactive management of white mold (Sclerotinia sclerotiorum) in snap beans and present updates on yield assessment for beets and harvest scheduling for beans. The specific study areas are located at Cornell AgriTech (previously, the New York State Agricultural Experiment Station; Geneva, NY). A DJI Matrice-600 UAS, boasting a high spatial resolution color camera, a Headwall Photonics imaging spectrometer (272 bands; 400-1000 nm), and a Velodyne VLP-16 lidar system were used for this research. Initial findings from these various projects will be presented, while focusing on i) the need for proper calibration-to-reflectance of the imaging data, ii) identification of operational wavelength solutions from spectrally oversampled hyperspectral imagery, and iii) the benefit of fusing 3D lidar data alongside high-fidelity spectral imagery.
Bio. Jan van Aardt is a professor in the Chester F. Carlson Center for Imaging Science at the Rochester Institute of Technology, New York. He obtained a B.Sc. Forestry degree from the University of Stellenbosch, South Africa. He completed M.S. and Ph.D. Forestry degrees at Virginia Tech (Blacksburg, VA), focused on imaging spectroscopy and light detection and ranging applications, respectively. This was followed by post-doctoral work at the Katholieke Universiteit Leuven, Belgium, and a stint as research group leader at the Council for Scientific and Industrial Research, South Africa. Imaging spectroscopy and structural (lidar) sensing of natural resources form the core of his efforts, which vary between vegetation structural and system state (physiology) assessment. His research group makes use of both real and simulated data, where the latter is rooted in first-principles, physics-based tools. He has received funding from NSF, NASA, NGA, Google, USFS, and USDA, among others, and he has published >90 peer-reviewed papers and >100 conference contributions.