Machine Learning and Sensing Lab Alumni, Anand Seethepalli, and collaborators recently had a paper accepted to Plant Phenomics. The article discusses an innovative platform to help collect consistent images of root crowns for phenotyping. Check it out here!
Journal PapersJournal Papers
Peanut Maturity Classification using Hyperspectral Imagery
Abstract: Seed maturity in peanut ( Arachis hypogaea L.) determines economic return to a producer because of its impact on seed weight, and critically influences seed vigor and other quality characteristics. During seed development, the inner mesocarp layer of the… Read More
Breaking down barriers between remote sensing and plant pathology
Abstract: A critical component for enhancing productivity and quality of food and fiber is the ability to quickly detect and monitor plant diseases in order to prevent or minimize losses to agricultural and forest products (Mahlein 2016). The earlier (prior to… Read More
Classifying California plant species temporally using airborne hyperspectral imagery
Abstract: Accurate knowledge of seasonal and inter-annual distributions of plant species is required for many research and management agendas that track ecosystem health. Airborne imaging spectroscopy data have been used successfully to map plant species, but often only in a… Read More
Plant species’ spectral emissivity and temperature using the hyperspectral thermal emission spectrometer (HyTES) sensor
Abstract: The thermal domain (TIR; 2.5–15 μm) delivers unique measurements of plant characteristics that are not possible in other parts of the electromagnetic spectrum. However, these TIR measurements have largely been restricted to laboratory leaf level or coarse spatial resolutions… Read More
The ECOSTRESS spectral library version 1.0. Remote Sensing of Environment
Abstract: In June 2018, the ECOsystem Spaceborne Thermal Radiometer Experiment on Space Station (ECOSTRESS) mission was launched to measure plant temperatures and better understand how they respond to stress. While the ECOSTRESS mission delivers imagery with ~60 m spatial resolution,… Read More
Individual tree-crown detection in RGB imagery using semi-supervised deep learning neural networks
Abstract: Remote sensing can transform the speed, scale, and cost of biodiversity and forestry surveys. Data acquisition currently outpaces the ability to identify individual organisms in high resolution imagery. We outline an approach for identifying tree-crowns in true color, or… Read More
Overcoming Small Minirhizotron Datasets Using Transfer Learning
Abstract: Minirhizotron technology is widely used for studying the development of roots. Such systems collect visible-wavelength color imagery of plant roots in-situ by scanning an imaging system within a clear tube driven into the soil. Automated analysis of root systems… Read More
RhizoVision Crown: An Integrated Hardware and Software Platform for Root Crown Phenotyping
Abstract: Root crown phenotyping measures the top portion of crop root systems and can be used for marker-assisted breeding, genetic mapping, and understanding how roots influence soil resource acquisition. Several imaging protocols and image analysis programs exist, but they are… Read More
Root Identification in Minirhizotron Imagery with Multiple Instance Learning
Abstract: In this paper, multiple instance learning (MIL) algorithms to automatically perform root detection and segmentation in minirhizotron imagery using only image-level labels are proposed. Root and soil characteristics vary from location to location, thus, supervised machine learning approaches that… Read More