Unsupervised Pre-Training for 3D Leaf Instance Segmentation

Abstract

Crops for food, feed, fiber, and fuel are key natural resources for our society. Monitoring plants and measuring their traits is an important task in agriculture often referred to as plant phenotyping. Traditionally, this task is done manually, which is time- and labor-intensive. Robots can automate phenotyping providing reproducible and high-frequency measurements. Today's perception systems use deep learning to interpret these measurements, but require a substantial amount of annotated data to work well. Obtaining such labels is challenging as it often requires background knowledge on the side of the labelers. This paper addresses the problem of reducing the labeling effort required to perform leaf instance segmentation on 3D point clouds, which is a first step toward phenotyping in 3D. Separating all leaves allows us to count them and compute relevant traits as their areas, lengths, and widths. We propose a novel self-supervised task-specific pre-training approach to initialize the backbone of a network for leaf instance segmentation. We also introduce a novel automatic postprocessing that considers the difficulty of correctly segmenting the points close to the stem, where all the leaves petiole overlap. The experiments presented in this paper suggest that our approach boosts the performance over all the investigated scenarios. We also evaluate the embeddings to assess the quality of the fully unsupervised approach and see a higher performance of our domain-specific postprocessing.

Plant phenotyping relevance

3D点群から葉を個体別に分割し、面積・長さ・幅などの形質を抽出する計算手法を開発・評価しており、植物フェノタイピング手法が中心である。

Code and data availability

The supplied blocks describe UAV-collected sugar beet point clouds and self-supervised pre-training experiments, but contain no data availability statement, no public dataset deposit, and no author code release URL. The only URL present is the IEEE rights notice, which is not a paper-specific asset.

No evidence-backed public reproduction asset is currently recorded.