What Does TERRA-REF’s High Resolution, Multi Sensor Plant Sensing Public Domain Data Offer the Computer Vision Community?

  title={What Does TERRA-REF’s High Resolution, Multi Sensor Plant Sensing Public Domain Data Offer the Computer Vision Community?},
  author={David LeBauer and Maxwell Burnette and N. Fahlgren and Rob Kooper and Kenton McHenry and Abby Stylianou},
  journal={2021 IEEE/CVF International Conference on Computer Vision Workshops (ICCVW)},
A core objective of the TERRA-REF project was to generate an open-access reference dataset for the evaluation of sensing technologies to study plants under field conditions. The TERRA-REF program deployed a suite of high-resolution, cutting edge technology sensors on a gantry system with the aim of scanning 1 hectare (104m) at around 1 mm2 spatial resolution multiple times per week. The system contains co-located sensors including a stereo-pair RGB camera, a thermal imager, a laser scanner to… 

Figures and Tables from this paper

The Global Assessment of Oilseed Brassica Crop Species Yield, Yield Stability and the Underlying Genetics

The global demand for oilseeds is increasing along with the human population. The family of Brassicaceae crops are no exception, typically harvested as a valuable source of oil, rich in beneficial



TERRA-REF Data Processing Infrastructure

The technical architecture for the TERRA-REF data and computing pipeline provides a suite of components to convert raw imagery to standard formats, geospatially subset data, and identify biophysical and physiological plant features related to crop productivity, resource use, and stress tolerance.

A New Optical Remote Sensing Technique for High-Resolution Mapping of Soil Moisture

These findings and the presented framework can be applied in conjunction with Unmanned Aerial System observations to assist with farm scale precision irrigation management to improve water use efficiency of cropping systems and conserve water in water-limited regions of the world.

Data-Driven Artificial Intelligence for Calibration of Hyperspectral Big Data

Near-earth hyperspectral big data present both huge opportunities and challenges for spurring developments in agriculture and high-throughput plant phenotyping and breeding. In this article, we

Multi-resolution Outlier Pooling for Sorghum Classification

The Sorghum-100 dataset is introduced, a large dataset of RGB imagery of sorghum captured by a state-of-the-art gantry system, a multi-resolution network architecture that learns both global and fine-grained features on the crops, and a newglobal pooling strategy called Dynamic Outlier Pooling which outperforms standard global pooling strategies on this task.

An open, scalable, and flexible framework for automated aerial measurement of field experiments

An initial draft of the Drone Processing Pipeline (DPP) is presented, a framework for processing agricultural research imagery that supports best practices and interoperability and is designed to create a processing pipeline that is open, flexible, extensible, portable, and automated.

Leaf optical properties reflect variation in photosynthetic metabolism and its sensitivity to temperature

Fresh-leaf reflectance spectroscopy and a partial least-squares regression analysis were used to estimate key determinants of photosynthetic capacity—namely the maximum rates of RuBP carboxylation (Vcmax) and regeneration (Jmax)—measured with standard gas exchange techniques on leaves of trembling aspen and eastern cottonwood trees.

Chlorophyll fluorescence imaging captures photochemical efficiency of grain sorghum (Sorghum bicolor) in a field setting

To test and validate a field-deployed fluorescence imaging system on the TERRA-REF field scanalyzer, leaves of potted sorghum plants were treated with a photosystem II inhibitor, DCMU, to reduce photochemical efficiency (FV/FM).

Global Wheat Head Dataset 2021: more diversity to improve the benchmarking of wheat head localization methods

A new version of the Global Wheat Head Detection (GWHD) dataset in 2021 is released, which is bigger, more diverse, and less noisy than the 2020 version.