Geometrical Stem Detection from Image Data for Precision Agriculture

TL;DR

This paper presents a fully automatic method for detecting plant stems from RGB images in precision agriculture, enabling accurate weed removal and crop analysis with real-time processing on mobile robots.

Contribution

It introduces a novel approach for automatic stem detection from RGB images, including leaf separation and stem localization, suitable for deployment on mobile agricultural robots.

Findings

Detects leaves and estimates stem positions at 56 Hz on a single CPU.

Validated on three datasets with ground truth.

Provides open-source software for the community.

Abstract

High efficiency in precision farming depends on accurate tools to perform weed detection and mapping of crops. This allows for precise removal of harmful weeds with a lower amount of pesticides, as well as increase of the harvest's yield by providing the farmer with valuable information. In this paper, we address the problem of fully automatic stem detection from image data for this purpose. Our approach runs on mobile agricultural robots taking RGB images. After processing the images to obtain a vegetation mask, our approach separates each plant into its individual leaves and later estimates a precise stem position. This allows an upstream mapping algorithm to add the high-resolution stem positions as a semantic aggregate to the global map of the robot, which can be used for weeding and for analyzing crop statistics. We implemented our approach and thoroughly tested it on three different datasets with vegetation masks and stem position ground truth. The experiments presented in this paper conclude that our module is able to detect leaves and estimate the stem's position at a rate of 56 Hz on a single CPU. We furthermore provide the software to the community.