Karl-Heinz Dammer

Strategy for the Development of a Smart NDVI Camera System for Outdoor Plant Detection and Agricultural Embedded Systems

The application of (smart) cameras for process control, mapping, and advanced imaging in agriculture has become an element of precision farming that facilitates the conservation of fertilizer, pesticides, and machine time. This technique additionally reduces the amount of energy required in terms of fuel. Although research activities have increased in this field, high camera prices reflect low adaptation to applications in all fields of agriculture. Smart, low-cost cameras adapted for agricultural applications can overcome this drawback. The normalized difference vegetation index (NDVI) for each image pixel is an applicable algorithm to discriminate plant information from the soil background enabled by a large difference in the reflectance between the near infrared (NIR) and the red channel optical frequency band. Two aligned charge coupled device (CCD) chips for the red and NIR channel are typically used, but they are expensive because of the precise optical alignment required. Therefore, much attention has been given to the development of alternative camera designs. In this study, the advantage of a smart one-chip camera design with NDVI image performance is demonstrated in terms of low cost and simplified design. The required assembly and pixel modifications are described, and new algorithms for establishing an enhanced NDVI image quality for data processing are discussed.

Monitoring Agronomic Parameters of Winter Wheat Crops with Low-Cost UAV Imagery

Monitoring the dynamics in wheat crops requires near-term observations with high spatial resolution due to the complex factors influencing wheat growth variability. We studied the prospects for monitoring the biophysical parameters and nitrogen status in wheat crops with low-cost imagery acquired from unmanned aerial vehicles (UAV) over an 11 ha field. Flight missions were conducted at approximately 50 m in altitude with a commercial copter and camera system—three missions were performed between booting and maturing of the wheat plants and one mission after tillage. Ultra-high resolution orthoimages of 1.2 cm·px−1 and surface models were generated for each mission from the standard red, green and blue (RGB) aerial images. The image variables were extracted from image tone and surface models, e.g., RGB ratios, crop coverage and plant height. During each mission, 20 plots within the wheat canopy with 1 × 1 m2 sample support were selected in the field, and the leaf area index, plant height, fresh and dry biomass and nitrogen concentrations were measured. From the generated UAV imagery, we were able to follow the changes in early senescence at the individual plant level in the wheat crops. Changes in the pattern of the wheat canopy varied drastically from one mission to the next, which supported the need for instantaneous observations, as delivered by UAV imagery. The correlations between the biophysical parameters and image variables were highly significant during each mission, and the regression models calculated with the principal components of the image variables yielded R2 values between 0.70 and 0.97. In contrast, the models of the nitrogen concentrations yielded low R2 values with the best model obtained at flowering (R2 = 0.65). The nitrogen nutrition index was calculated with an accuracy of 0.10 to 0.11 NNI for each mission. For all models, information about the surface models and image tone was important. We conclude that low-cost RGB UAV imagery will strongly aid farmers in observing biophysical characteristics, but it is limited for observing the nitrogen status within wheat crops.

Estimating wheat biomass by combining image clustering with crop height

Light scattering by ears, stems and twisted leaves obstructed NDVI segmentation.Partitioning clustering algorithms performed equally for biomass estimation.Wheat biomass estimation by image clustering was time- and location dependent.Calibration needs were prevented by combining image clustering with plant height. Site-specific management strategies in wheat fields can be strongly enhanced with sensor technology that detects spatial changes of wheat biomass. The objectives of this study were to propose a multi-sensor approach combining a digital camera system that measures plant coverage with an arbitrary crop height measuring instrument for estimating wheat biomass. Digital images, fresh and dry biomass, and crop height measurements were taken at 180 sample points distributed over 4 fields between the BBCH growth stages 30-75. Plant coverage percentage was calculated by separating plant pixels from background pixels of NDVI and NIR images using image segmentation based on partitioning clustering. Performance of three clustering algorithms (k-means, partition around mediods (PAM), and fuzzy c-means) was analyzed. Plant coverage from image clustering was further related to fresh and dry biomass with and without crop height measurements using simple and multiple regression models. The performance of the three clustering algorithms was similar for estimating wheat biomass. NDVI image segmentation was highly obstructed by scattering effects especially at later BBCH stages through the presence of wheat ears, stems, and tilted leaves, whereas NIR image segmentation was generally good except with images that were taken at locations with very low plant coverage and dry soil crusts. Consequently, NIR image clustering yielded more accurate estimates of fresh and dry biomass (R2=0.79/0.68) than NDVI image clustering (R2=0.66/0.56) among the individual measurement runs on average. Still cloud conditions had some influence on NIR clustering. By pooling the complete set of sampling points from all measurement runs into a global model, the combination of image clustering with crop height was helpful. For fresh biomass, global model quality changed from R2=0.15 or R2=0.46 without crop height to R2=0.63 or R2=0.82 with crop height for NDVI or NIR, respectively. For dry biomass, crop height was itself a strong predictor with R2=0.86, whereas the model improvement by including image clustering of plant coverage was nearly negligible. In conclusion, the combination of a camera sensor using image clustering with a sensor able to measure crop height such as LIDAR or ultrasound systems seems to be a promising way to reach for more accurate and robust estimations of wheat biomass especially when measurements over multiple fields and dates are considered without the need of re-calibration.

Sensor‐based variable‐rate fungicide application in winter wheat

BACKGROUND Currently, no technology for the automatic detection of diseases while moving agricultural equipment through fields is available on the market. An alternative approach of target-oriented fungicide spraying was tested to adapt the local dose rates of spray liquid in winter wheat to local differences in the plant surface and biomass by using a camera sensor. RESULTS A linear correlation was found between the sensor values and two plant parameters, namely the leaf area index and biomass. The spray volume was linearly adapted to the local sensor value in a field trial. The camera sensor was used to operate the dosing system (gauge) at the field boom sprayer. A total of 8% of spray liquid was saved compared with common uniform spraying. CONCLUSIONS Because no differences exist in yield and disease incidence between the sensor-based and uniformly sprayed plot, this new technology, which uses plants as targets for fungicide dosages, could be an alternative to the present common dosage practices on a hectare basis.

Variable Rate ApplicationVariable rate application of Fungicides

Plant diseases often occur in patches within the field. But real-time sensor technology for automatic disease detection which would be a prerequisite for demand related fungicide application is commercially not yet available. In heterogeneous fields growth conditions vary greatly due to soil quality differences. Consequently there exist subareas with varying biomass which affect yield at harvest time. In high biomass and yield subareas the Leaf Area Index (LAI) is greater than in low biomass subareas. In cereals LAI can serve as a parameter to adapt application rate to the growth differences in fields. Sensor controlled variable rate field sprayer technology therefore meets the economic and ecological demands of process optimisation in the production of primary plant goods.

Regression Kriging for Improving Crop Height Models Fusing Ultra-Sonic Sensing with UAV Imagery

A crop height model (CHM) can be an important element of the decision making process in agriculture, because it relates well with many agronomic parameters, e.g., crop height, plant biomass or crop yield. Today, CHMs can be inexpensively obtained from overlapping imagery captured from unmanned aerial vehicle (UAV) platforms or from proximal sensors attached to ground-based vehicles used for regular management. Both approaches have their limitations and combining them with a data fusion may overcome some of these limitations. Therefore, the objective of this study was to investigate if regression kriging, as a geostatistical data fusion approach, can be used to improve the interpolation of ground-based ultrasonic measurements with UAV imagery as covariate. Regression kriging might be suitable because we have a sparse data set (ultrasound) and an exhaustive data set (UAV) and both data sets have favorable properties for geostatistical analysis. To confirm this, we conducted four missions in two different fields in total, where we collected UAV imagery and ultrasonic data alongside. From the overlapping UAV images, surface models and ortho-images were generated with photogrammetric processing. The maps generated by regression kriging were of much higher detail than the smooth maps generated by ordinary kriging, because regression kriging ensures that for each prediction point information from the UAV, imagery is given. The relationship with crop height, fresh biomass and, to a lesser extent, with crop yield, was stronger using CHMs generated by regression kriging than by ordinary kriging. The use of UAV data from the prior mission was also of benefit and could improve map accuracy and quality. Thus, regression kriging is a flexible approach for the integration of UAV imagery with ground-based sensor data, with benefits for precision agriculture-oriented farmers and agricultural service providers.

On-the-go Phenotyping in Field Potatoes Using Camera Vision

A camera sensor for detecting crop parameters, with the aim of implementing precision plant protection, has been developed at the Leibniz Institute for Agricultural Engineering. This sensor was tested in farmers’ potato fields regarding the phenotyping and monitoring of crop growth. Field trials were conducted in 2007, 2011 and 2012 to quantify the relationship between the sensor measurements of the coverage level by the green stem and leaf parts and two plant parameters: the fresh mass of the tops and the leaf area index. Within the fields, sampling points were chosen based on differences in crop development. At different dates, the sensor values (coverage level) and the two plant parameters were determined. Because of the shape of the obtained scatterplots between the two plant parameters and the coverage level, a linear regression model with a plateau was adapted. An on-the-go (on-line, real-time) technology for measuring the percentage of green coverage was tested to monitor the development of the potato crop during the growth period. The sensor was positioned on the left side of the tractor to scan the crop stand along transects. The coverage level was measured and recorded together with the geographical position using a data processing system. Areas showing different plant growth could be determined, as could differences in the temporal development of the crop in the various sections of the transect.

Discrimination of Common Ragweed (Ambrosia artemisiifolia) and Mugwort (Artemisia vulgaris) Based on Bag of Visual Words Model

Common ragweed is a plant species causing allergic and asthmatic symptoms in humans. To control its propagation, an early identification system is needed. However, due to its similar appearance with mugwort, proper differentiation between these two weed species is important. Therefore, we propose a method to discriminate common ragweed and mugwort leaves based on digital images using bag of visual words (BoVW). BoVW is an object-based image classification that has gained acceptance in many areas of science. We compared speeded-up robust features (SURF) and grid sampling for keypoint selection. The image vocabulary was built using K-means clustering. The image classifier was trained using support vector machines. To check the robustness of the classifier, specific model runs were conducted with and without damaged leaves in the trainings dataset. The results showed that the BoVW model allows the discrimination between common ragweed and mugwort leaves with high accuracy. Based on SURF keypoints with 50% of 788 images in total as training data, we achieved a 100% correct recognition of the two plant species. The grid sampling resulted in slightly less recognition accuracy (98 to 99%). In addition, the classification based on SURF was up to 31 times faster. Nomenclature: Common ragweed, Ambrosia artemisiifolia L.; mugwort, Artemisia vulgaris L.

Impact of sensor-controlled variable-rate fungicide application on yield, senescence and disease occurrence in winter wheat fields: Impact of sensor-controlled fungicide application on winter wheat

BACKGROUND Field experiments examining target-oriented variable-rate fungicide spraying were performed in 2015 and 2016. The spray volume was adapted in real time to the local green coverage level of winter wheat (Triticum aestivum L.), which was detected using a camera sensor. RESULTS Depending on the growth heterogeneity in the three strip trials in 2015, fungicide savings in the sensor-sprayed strip compared with the adjacent uniformly sprayed strip were 44%, 45% and 1%. In the 2016 field trial, the saving was 12%. There was no greater level of senescence or disease occurrence, and no higher yield losses in the camera-controlled variable-rate sprayed strips compared with the adjacent uniformly sprayed strips. CONCLUSIONS From an ecological and economical point of view, sensor-controlled variable-rate spraying technology, which uses the level of green crop coverage as the plant parameter to adapt the spray volume locally, can be an alternative to the common practice of uniform spraying.

Vegetationserkennung für landwirtschaftliche Anwendungen mithilfe einer Ein-Chip-Kamera

Durch die Anwendung von Kameras bei der Prozesskontrolle in der Prazisionslandwirtschaft konnen Dunger, Pestizide, Maschinenzeit und Treibstoff eingespart werden. Trotz der hohen Forschungsaktivitaten auf diesem Gebiet verhindern hohe Preise fur geeignete Kamerasysteme die Anwendung in allen Bereichen der Landwirtschaft. Intelligente und kostengunstige Kameras, die fur landwirtschaftliche Anwendungen angepasst werden, konnen diesen Nachteil uberwinden. Der normalisierte differenzierte Vegetationsindex (NDVI) ist ein Algorithmus in der Bildanalyse zur Trennung von Pflanze und Boden (Hintergrund) und wird in der hier vorgestellten Untersuchung bei einer kostengunstigen Ein-Chip-Kamera implementiert und angepasst.