AutoCount: Unsupervised Segmentation and Counting of Organs in Field Images

TL;DR

AutoCount introduces an unsupervised method for segmenting and counting plant organs in outdoor images, eliminating the need for manual annotations and achieving competitive results in plant phenotyping tasks.

Contribution

It presents a novel fully unsupervised approach combining segmentation and optimization for counting plant organs without dataset-specific tuning.

Findings

Achieves competitive counting accuracy on sorghum and wheat images.

Does not require dataset-dependent tuning or annotations.

Demonstrates effectiveness in real-world plant phenotyping scenarios.

Abstract

Counting plant organs such as heads or tassels from outdoor imagery is a popular benchmark computer vision task in plant phenotyping, which has been previously investigated in the literature using state-of-the-art supervised deep learning techniques. However, the annotation of organs in field images is time-consuming and prone to errors. In this paper, we propose a fully unsupervised technique for counting dense objects such as plant organs. We use a convolutional network-based unsupervised segmentation method followed by two post-hoc optimization steps. The proposed technique is shown to provide competitive counting performance on a range of organ counting tasks in sorghum (S. bicolor) and wheat (T. aestivum) with no dataset-dependent tuning or modifications.