For achieving precise and automatic growth analysis and prediction of plants, it is mandatory to obtain plant structure (i.e. branching patterns and leaf locations). Using state-of-the-art computer vision approaches using multi-view images, this project tackles the plant structure modeling problem, where branches are occluded by numbers of leaves. I also deal with the generation of plant lifelog, which consists of time-series plant structure and information from the field sensing, contributing the future of the cultivation.

Grants

• 2017/10 – 2021/9 JST PRESTO
  Innovational technical basis for cultivation in cooperation with information science
  「Three-dimensional plant structure modeling and lifelog generation for growth analysis and prediction in future cultivation」
  PI: Fumio Okura, Grant: 31,300K JPY

Publications

• Yosuke Toda, Fumio Okura, Jun Ito, Satoshi Okada, Toshinori Kinoshita, Hiroyuki Tsuji, Daisuke Saisho. Training instance segmentation neural network with synthetic datasets for crop seed phenotyping. Communications Biology, Vol. 3, Article 173, Apr 2020. 
• Yosuke Toda, Fumio Okura. How convolutional neural networks diagnose plant disease. Plant Phenomics, Article ID 9237136, 14 pages, Mar 2019. 
• Takuma Doi, Fumio Okura, Toshiki Nagahara, Yasuyuki Matsushita, Yasushi Yagi. Descriptor-free multi-view region matching for instance-wise 3D reconstruction. Proceedings of Asian Conference on Computer Vision (ACCV), (oral), Dec 2020.
• Fumio Okura, Saya Ikuma, Yasushi Makihara, Daigo Muramatsu, Ken Nakada, Yasushi Yagi. RGB-D video-based individual identification of dairy cows using gait and texture analyses. Computers and Electronics in Agriculture (COMPAG), Vol. 165, Article 104944, Oct 2019.
• *Takahiro Isokane, *Fumio Okura, Ayaka Ide, Yasuyuki Matsushita, Yasushi Yagi. Probabilistic plant modeling via multi-view image-to-image translation. Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 2906-2915, Jun 2018.
•