The article presents an exploration of how the application of semantics and environmental priors can aid in constructing accurate 3D maps for agricultural purposes, specifically for the sorghum plant. The researchers use sorghum seeds as semantic landmarks to build a visual Simultaneous Localization and Mapping (SLAM) system that allows for a more comprehensive mapping of a sorghum range. Furthermore, the seeds are used as semantic features to enhance the 3D reconstruction of a full sorghum panicle from images captured by a robotic in-hand camera.
Publication date: 29 Dec 2023
Project Page: https://www.ri.cmu.edu/
Paper: https://arxiv.org/pdf/2312.17110
