Marion Deichmann
Type of resources
Keywords
Contact for the resource
Provided by
-
The dataset RGB-MiniplotBarley contains 22164 RGB images of 11 time points 21. jun - 7. jul 2022 of two genotypes of spring barley grown under single-nutrient deficiencies of N, P, K, S, B and one multi-nutrient deficient treatment from miniplot fertilizer trial at Campus Klein-Altendorf of University of Bonn. The images are annotated with plot number, genotype and fertilizer management and have been taken for a Deep Learning approach for nutrient deficiency recognition.
-
The dataset RGB-varCereals-LTFT-Bonn contains 16717 RGB images of 17 time points 14. apr - 29. jul 2021 of barley, rye and wheat from long-term field fertilizer trial Dikopshof at University of Bonn. The images are annotated with crop, genotype and fertilizer management and have been taken for a Deep Learning approach for nutrient deficiency recognition.
-
The dataset RGB-SoilPotWheat contains 39463 RGB images of 10 time points 23. Feb - 22. March 2021 of four genotypes of winter wheat from a pot experiment in greenhouse at University of Bonn. The images are annotated by potnumber which encodes genotype and fertilizer management and have been taken for a Deep Learning approach for nutrient deficiency recognition.
-
The dataset RGB-divCrops-LTFT-Halle2 contains 6434 RGB images of 2 time points 3.+ 15. jun 2022 of barley, potatoe, rye, sugar beet and wheat from long-term field fertilizer trial at University of Halle. The images are annotated with crop and fertilizer management and have been taken for a Deep Learning approach for nutrient deficiency recognition.
-
The dataset RGB-HydroBarley3 contains 12258 RGB images of 6 time points 22. jun - 10. jul 2020 of four genotypes of spring barley from a hydroponic experiment in greenhouse at University of Bonn including single-nutrient deficiencies of all 14 essential mineral nutrients plus Al and Mn toxicity. The images are annotated with genotype and fertilizer management and have been taken for a Deep Learning approach for nutrient deficiency recognition.
-
The dataset RGB-HydroBarley2 contains 15647 RGB images of 8 time points 19. March - 16. April 2020 of four genotypes of spring barley from a hydroponic experiment in greenhouse at University of Bonn including single-nutrient deficiencies of all 14 essential mineral nutrients plus Al toxicity. The images are annotated with genotype and fertilizer management and have been taken for a Deep Learning approach for nutrient deficiency recognition.
-
The dataset RGB-HydroWheat1 contains 16298 RGB images of 8 time points 11. may - 4. jun 2020 of five genotypes of winter wheat from a hydroponic experiment in greenhouse at University of Bonn including single-nutrient deficiencies of all 14 essential mineral nutrients plus Al and Mn toxicities. The images are annotated with genotype and fertilizer management and have been taken for a Deep Learning approach for nutrient deficiency recognition.
-
The dataset RGB-Wheat-LTFT-Bonn contains 7361 RGB images of 22 time points 6. Feb. - 12. June 2020 of winter wheat variety 'Boss' from long-term field fertilizer trial at University of Bonn. The images are annotated with crop, variety and fertilizer management, including single-nutrient omission of N, P and K, a treatment without liming, an unfertilized treatment, ctrl and ctrl plus manure, and have been taken for a Deep Learning approach for nutrient deficiency recognition.
-
The dataset RGB-SoilPotBarley contains 35,343 RGB images of 8 time points 22. dec 2020 - 21. jan 2021 of four genotypes of spring barley from a pot experiment in greenhouse at University of Bonn. The images are annotated by potnumber which encodes genotype and fertilizer management and have been taken for a Deep Learning approach for nutrient deficiency recognition.
-
The dataset RGB-divCrops-LTFT-Halle1 contains 8689 RGB images of 16 time points 9. apr - 19. aug 2021 of barley, potatoe, rye, sugar beet and wheat from long-term field fertilizer trial at University of Halle. The images are annotated with crop and fertilizer management and have been taken for a Deep Learning approach for nutrient deficiency recognition.