From Seedling to Harvest: The GrowingSoy Dataset for Weed Detection in Soy Crops via Instance Segmentation

TL;DR

This paper introduces the GrowingSoy dataset with 1,000 annotated images for instance segmentation of weeds and soy plants, demonstrating high accuracy with state-of-the-art models across different growth stages.

Contribution

The work provides a new comprehensive dataset and benchmarks for weed and soy plant detection using instance segmentation in agriculture.

Findings

Achieved 79.1% segmentation average precision with YOLOv8X

Attained 78.7% mAP-50 in weed segmentation with YOLOv8M

Demonstrated effective detection across all growth stages

Abstract

Deep learning, particularly Convolutional Neural Networks (CNNs), has gained significant attention for its effectiveness in computer vision, especially in agricultural tasks. Recent advancements in instance segmentation have improved image classification accuracy. In this work, we introduce a comprehensive dataset for training neural networks to detect weeds and soy plants through instance segmentation. Our dataset covers various stages of soy growth, offering a chronological perspective on weed invasion's impact, with 1,000 meticulously annotated images. We also provide 6 state of the art models, trained in this dataset, that can understand and detect soy and weed in every stage of the plantation process. By using this dataset for weed and soy segmentation, we achieved a segmentation average precision of 79.1% and an average recall of 69.2% across all plant classes, with the YOLOv8X model. Moreover, the YOLOv8M model attained 78.7% mean average precision (mAp-50) in caruru weed segmentation, 69.7% in grassy weed segmentation, and 90.1% in soy plant segmentation.