The Oil Radish Growth Dataset for Semantic Segmentation and Yield Estimation

Anders Krogh Mortensen, Soren Skovsen, Henrik Karstoft, Rene Gislum; Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, 2019, pp. 0-0

Data sharing in research is important in order to reproduce results, develop global models, and benchmark methods. This paper presents a dataset containing image and field data from a field plot experiment with oil radish (Raphanus sativus L. var oleiformis) as catch crop after spring barley. The field data consists of fresh weight, dry weight, Carbon content and Nitrogen content from multiple weekly plant samples collected from the plots. The image data consists of images collected weekly prior to the plant samples. A subset of the images corresponding to the plant sampling areas have been annotated pixelwise. In addition to the image and field data, weather data from the growing period is also included in the dataset. The dataset is accompanied by two challenges: 1) semantic segmentation of crops and 2) oil radish yield estimation. The former challenge focuses on data image, while the latter focuses on the field data. Baseline methods and results are provided for both challenges.