Frank Liebisch

Plant phenotyping: from bean weighing to image analysis

Plant phenotyping refers to a quantitative description of the plant’s anatomical, ontogenetical, physiological and biochemical properties. Today, rapid developments are taking place in the field of non-destructive, image-analysis -based phenotyping that allow for a characterization of plant traits in high-throughput. During the last decade, ‘the field of image-based phenotyping has broadened its focus from the initial characterization of single-plant traits in controlled conditions towards ‘real-life’ applications of robust field techniques in plant plots and canopies. An important component of successful phenotyping approaches is the holistic characterization of plant performance that can be achieved with several methodologies, ranging from multispectral image analyses via thermographical analyses to growth measurements, also taking root phenotypes into account.

Remote, aerial phenotyping of maize traits with a mobile multi-sensor approach.

BackgroundField-based high throughput phenotyping is a bottleneck for crop breeding research. We present a novel method for repeated remote phenotyping of maize genotypes using the Zeppelin NT aircraft as an experimental sensor platform. The system has the advantage of a low altitude and cruising speed compared to many drones or airplanes, thus enhancing image resolution while reducing blurring effects. Additionally there was no restriction in sensor weight. Using the platform, red, green and blue colour space (RGB), normalized difference vegetation index (NDVI) and thermal images were acquired throughout the growing season and compared with traits measured on the ground. Ground control points were used to co-register the images and to overlay them with a plot map.ResultsNDVI images were better suited than RGB images to segment plants from soil background leading to two separate traits: the canopy cover (CC) and its NDVI value (NDVIPlant). Remotely sensed CC correlated well with plant density, early vigour, leaf size, and radiation interception. NDVIPlant was less well related to ground truth data. However, it related well to the vigour rating, leaf area index (LAI) and leaf biomass around flowering and to very late senescence rating. Unexpectedly, NDVIPlant correlated negatively with chlorophyll meter measurements. This could be explained, at least partially, by methodical differences between the used devices and effects imposed by the population structure. Thermal images revealed information about the combination of radiation interception, early vigour, biomass, plant height and LAI. Based on repeatability values, we consider two row plots as best choice to balance between precision and available field space. However, for thermography, more than two rows improve the precision.ConclusionsWe made important steps towards automated processing of remotely sensed data, and demonstrated the value of several procedural steps, facilitating the application in plant genetics and breeding. Important developments are: the ability to monitor throughout the season, robust image segmentation and the identification of individual plots in images from different sensor types at different dates. Remaining bottlenecks are: sufficient ground resolution, particularly for thermal imaging, as well as a deeper understanding of the relatedness of remotely sensed data and basic crop characteristics.

The ETH field phenotyping platform FIP: A cable-suspended multi-sensor system

Crop phenotyping is a major bottleneck in current plant research. Field-based high-throughput phenotyping platforms are an important prerequisite to advance crop breeding. We developed a cable-suspended field phenotyping platform covering an area of ~1ha. The system operates from 2 to 5m above the canopy, enabling a high image resolution. It can carry payloads of up to 12kg and can be operated under adverse weather conditions. This ensures regular measurements throughout the growing period even during cold, windy and moist conditions. Multiple sensors capture the reflectance spectrum, temperature, height or architecture of the canopy. Monitoring from early development to maturity at high temporal resolution allows the determination of dynamic traits and their correlation to environmental conditions throughout the entire season. We demonstrate the capabilities of the system with respect to monitoring canopy cover, canopy height and traits related to thermal and multi-spectral imaging by selected examples from winter wheat, maize and soybean. The system is discussed in the context of other, recently established field phenotyping approaches; such as ground-operating or aerial vehicles, which impose traffic on the field or require a higher distance to the canopy.

Beyond point clouds - 3D mapping and field parameter measurements using UAVs

Recent developments in Unmanned Aerial Vehicles (UAVs) have made them ideal tools for remotely monitoring agricultural fields. Complementary advancements in computer vision have enabled automated post-processing of images to generate dense 3D reconstructions in the form of point clouds. In this paper we present a monitoring pipeline that uses a readily available, low cost UAV and camera for quickly surveying a winter wheat field, generate a 3D point cloud from the collected imagery and present methods for automated crop height estimation from the extracted point cloud and compare our estimates with those using standardized techniques.

Characterization of crop vitality and resource use efficiency by means of combining imaging spectroscopy based plant traits

In this contribution measurements of the Airborne Prism Experiment (APEX) imaging spectrometer were used to derive products related to plant traits, e.g., leaf chlorophyll, carotenoid, anthocyanin, and water content, leaf greenness, biomass, and leaf area index. The Apex products were highly correlated to the related ground truth measurements in major crops under experimental and field situations. The relationship of APEX derived NDVI (NDVIAPEX) with ground measured NDVI and canopy cover is shown in detail. Additionally, interrelations between the aerial detected traits are discussed. The combination of the presented remotely measured plant traits can potentially give crop specific indications of their growth status and vitality. Such tools could help to improve resource use efficiency in agricultural systems and are needed for applications in precision agriculture and mapping of land use and land cover for scientific purposes or decision making.

Aerial and Ground Based Sensing of Tolerance to Beet Cyst Nematode in Sugar Beet

The rapid development of image-based phenotyping methods based on ground-operating devices or unmanned aerial vehicles (UAV) has increased our ability to evaluate traits of interest for crop breeding in the field. A field site infested with beet cyst nematode (BCN) and planted with four nematode susceptible cultivars and five tolerant cultivars was investigated at different times during the growing season. We compared the ability of spectral, hyperspectral, canopy height- and temperature information derived from handheld and UAV-borne sensors to discriminate susceptible and tolerant cultivars and to predict the final sugar beet yield. Spectral indices (SIs) related to chlorophyll, nitrogen or water allowed differentiating nematode susceptible and tolerant cultivars (cultivar type) from the same genetic background (breeder). Discrimination between the cultivar types was easier at advanced stages when the nematode pressure was stronger and the plants and canopies further developed. The canopy height (CH) allowed differentiating cultivar type as well but was much more efficient from the UAV compared to manual field assessment. Canopy temperatures also allowed ranking cultivars according to their nematode tolerance level. Combinations of SIs in multivariate analysis and decision trees improved differentiation of cultivar type and classification of genetic background. Thereby, SIs and canopy temperature proved to be suitable proxies for sugar yield prediction. The spectral information derived from handheld and the UAV-borne sensor did not match perfectly, but both analysis procedures allowed for discrimination between susceptible and tolerant cultivars. This was possible due to successful detection of traits related to BCN tolerance like chlorophyll, nitrogen and water content, which were reduced in cultivars with a low tolerance to BCN. The high correlation between SIs and final sugar beet yield makes the UAV hyperspectral imaging approach very suitable to improve farming practice via maps of yield potential or diseases. Moreover, the study shows the high potential of multi- sensor and parameter combinations for plant phenotyping purposes, in particular for data from UAV-borne sensors that allow for standardized and automated high-throughput data extraction procedures.

Impact of Plant Surface Moisture on Differential Interferometric Observables: A Controlled Electromagnetic Experiment

The estimation of soil moisture and crop biomass based on differential interferometry is questioned by the influence of intercepted rain (i.e., plant surface moisture) on repeat-pass observables. The magnitude, the origin of this effect, as well as its dependence on system and crop biophysical parameters have been only marginally addressed so far. This paper intends to investigate these aspects within the frame of a laboratory experiment carried out in a highly controlled electromagnetic environment. The collection of multifrequency and fully polarimetric scatterometer profiles offers a distinctive data set, which helps to understand the variations of the interferometric observables in response to a varying plant surface moisture. These changes are assessed by comparing the predictions of a first-order scattering solution with the impact found in the experimental data. Furthermore, the connection between plant surface moisture and differential interferometric observables (i.e., the magnitude and phase of the interferometric coherence) is empirically tested with the aid of regression techniques. Irrespective of frequency and polarization, intercepted water is found to impact the interferometric coherence in a similar way as changes in soil and/or plant water status, i.e., the increase of the sensor to target optical path. Changes of plant surface moisture might be erroneously mistaken either for soil water content or fresh biomass variations. Therefore, this paper raises the possibility that, in certain circumstances, intercepted water might represent a potential source of bias for the estimation of these two land surface parameters.

WeedMap: A Large-Scale Semantic Weed Mapping Framework Using Aerial Multispectral Imaging and Deep Neural Network for Precision Farming

We present a novel weed segmentation and mapping framework that processes multispectral images obtained from an unmanned aerial vehicle (UAV) using a deep neural network (DNN). Most studies on crop/weed semantic segmentation only consider single images for processing and classification. Images taken by UAVs often cover only a few hundred square meters with either color only or color and near-infrared (NIR) channels. Computing a single large and accurate vegetation map (e.g., crop/weed) using a DNN is non-trivial due to difficulties arising from: (1) limited ground sample distances (GSDs) in high-altitude datasets, (2) sacrificed resolution resulting from downsampling high-fidelity images, and (3) multispectral image alignment. To address these issues, we adopt a stand sliding window approach that operates on only small portions of multispectral orthomosaic maps (tiles), which are channel-wise aligned and calibrated radiometrically across the entire map. We define the tile size to be the same as that of the DNN input to avoid resolution loss. Compared to our baseline model (i.e., SegNet with 3 channel RGB inputs) yielding an area under the curve (AUC) of [background=0.607, crop=0.681, weed=0.576], our proposed model with 9 input channels achieves [0.839, 0.863, 0.782]. Additionally, we provide an extensive analysis of 20 trained models, both qualitatively and quantitatively, in order to evaluate the effects of varying input channels and tunable network hyperparameters. Furthermore, we release a large sugar beet/weed aerial dataset with expertly guided annotations for further research in the fields of remote sensing, precision agriculture, and agricultural robotics.

Real-Time Growth Analysis of Perennial Ryegrass Under Water Limiting Conditions

Understanding plant growth under abiotic stress conditions is very important for the development of tolerant crops. Here, we present a novel integrated phenotyping platform for investigating real-time growth of perennial ryegrass under abiotic stress using new technologies. In this work we demonstrate its use in studying leaf elongation rate with respect to temperature and soil moisture deficit. The method used is non-destructive, low labor intensive and applicable to other grass species.