TY  - CONF
AU  - Scharr, Hanno
AU  - Bruns, Benjamin
AU  - Fischbach, Andreas
AU  - Roussel, Johanna
AU  - Scholtes, Lukas
AU  - vom Stein, Jonas
TI  - Germination Detection of Seedlings in Soil: A System, Dataset and Challenge
VL  - 12540
CY  - Cambridge
PB  - Springer
M1  - FZJ-2021-00207
T2  - Lecture Notes in Computer Science
SP  - 360 - 374
PY  - 2020
AB  - In phenotyping experiments plants are often germinated in high numbers, and in a manual transplantation step selected and moved to single pots. Selection is based on visually derived germination date, visual size, or health inspection. Such values are often inaccurate, as evaluating thousands of tiny seedlings is tiring. We address these issues by quantifying germination detection with an automated, imaging-based device, and by a visual support system for inspection and transplantation. While this is a great help and reduces the need for visual inspection, accuracy of seedling detection is not yet sufficient to allow skipping the inspection step. We therefore present a new dataset and challenge containing 19.5k images taken by our germination detection system and manually verified labels. We describe in detail the involved automated system and handling setup. As baseline we report the performances of the currently applied color-segmentation based algorithm and of five transfer-learned deep neural networks.
T2  - 16th European Conference on Computer Vision
CY  - 23 Aug 2020 - 28 Aug 2020, Glasgow, UK (UK)
Y2  - 23 Aug 2020 - 28 Aug 2020
M2  - Glasgow, UK, UK
LB  - PUB:(DE-HGF)8 ; PUB:(DE-HGF)7
UR  - <Go to ISI:>//WOS:001500596600025
DO  - DOI:10.1007/978-3-030-65414-6_25
UR  - https://juser.fz-juelich.de/record/889315
ER  -