Challenges in automatic and selective plant-clearing
This work tackles the problem of sustainable forestry management for autonomous systems, but it appears incremental as it builds on existing plant segmentation methods.
The paper addresses the problem of automatic and selective plant-clearing in sustainable forestry, where an autonomous machine must detect and avoid specific plants while clearing weeds, and discusses challenges such as robustness to weather, plant variability, and database size.
With the advent of multispectral imagery and AI, there have been numerous works on automatic plant segmentation for purposes such as counting, picking, health monitoring, localized pesticide delivery, etc. In this paper, we tackle the related problem of automatic and selective plant-clearing in a sustainable forestry context, where an autonomous machine has to detect and avoid specific plants while clearing any weeds which may compete with the species being cultivated. Such an autonomous system requires a high level of robustness to weather conditions, plant variability, terrain and weeds while remaining cheap and easy to maintain. We notably discuss the lack of robustness of spectral imagery, investigate the impact of the reference database's size and discuss issues specific to AI systems operating in uncontrolled environments.