The application of methodologies to measure specific organism’s (e.g. plant, insect etc.) traits (morphology, growth etc.)  related to its structure and function is termed as phenotyping. With the emergence of low-cost and high-resolution multi-modal cameras, acquisition of 2D and 3D data permits high-throughput micro and macro analysis. This is a rapidly growing field at the interface of biology and computer vision (CV) termed- High-throughput Vision based Phenotyping. Unlike class objects e.g. car, table, chair etc. present in common datasets such as ImageNet; MSCOCO; PASCAL VOC and the SUN dataset, organisms are self changing systems with traits exhibiting variability. This poses novel challenges such as, tracking deformable objects e.g. microbes in microscopy imagery, multi-label segmentation of self-similar objects e.g. leave segmentation in plants, fish segmentation, 3D reconstruction in the presence of overlapping surfaces e.g. plant 3D structure reconstruction etc. In addition, the images acquired in natural conditions such as agricultural fields, greenhouses, forests, marine ecosystems introduce further complexity.

● Detection, multi-scale instance and semantic segmentation.

● Object tracking, optical flow and/or scene flow estimation.

● 3D modeling and segmentation.

● Denoising and Multi-modal image registration.

● Statistical shape analysis.

● Evaluation and benchmarking methodologies of automated image algorithms.

● Interactive Image Analysis.

● Learning in the face of little to no training data.

● Acquisition and analysis techniques. 

1. It will bring together the researchers working at the intersection of biology/phenomics and CV to solve problems with huge impact and potential to transform the natural ecosystems of plants or animals.

2. Open new avenues for collaboration amongst researchers and agricultural organizations, NGOs, local government bodies and other organizations to enable CV based beneficial research.

3. Define new, quantifiable, and impactful research questions/areas for the CV community.

4. New tools, datasets and projects can be promoted which would interest CV researchers to apply their skills on challenging phenomics problems.