Exploring the use of 3D point cloud data for improved plant stress rating

Shivani Chiranjeevi, Therin Young, Talukder Zaki Jubery, Koushik Nagasubramanian, Soumik Sarkar, Asheesh K Singh, Arti Singh, Baskar Ganapathysubramanian

Abstract: Currently, automated canopy stress classification for field crops relies on single-perspective, two-dimensional (2D) photographs, typically top view imaging via UAV. However, plant stress symptoms may appear throughout the canopy, and a single viewpoint photograph may not capture the entire region affected by the stress. Recent developments in efficient, large-scale, 3D point cloud capture of agricultural fields open up the possibility of more comprehensive stress identification and rating. We hypothesized that utilizing the 3D point cloud will allow multi-perspective construction of plant canopy, and subsequent training of more accurate plant stress identification and its rating in the field. We utilize an RGB 3D point cloud of a field where a diversity panel of soybean under Iron Deficiency chlorosis (IDC) stress was grown. We explore both multiview projection as well as area-preserving map projection methods to obtain parameterized 2D images depicting the complete 3D canopy surface. This approach allowed us to create models agnostic to canopy size/shape while allowing us to leverage pre-trained deep learning models -- trained on 2D image data. Our preliminary results are promising, and we continue to fine-tune these machine learning pipelines for classifying plant stress expression.