MatchPlant: An Open-Source Pipeline for UAV-Based Single-Plant Detection and Data Extraction
Accurate identification of individual plants from unmanned aerial vehicle (UAV) images is essential for advancing high-throughput phenotyping and supporting data-driven decision-making in plant breeding. This study presents MatchPlant, a modular, graphical user interface-supported, open-source Python pipeline for UAV-based single-plant detection and geospatial trait extraction. MatchPlant enables end-to-end workflows by integrating UAV image processing, user-guided annotation, Convolutional Neural Network model training for object detection, forward projection of bounding boxes onto an orthomosaic, and shapefile generation for spatial phenotypic analysis. In an early-season maize case study, MatchPlant achieved reliable detection performance (validation AP: 89.6%, test AP: 85.9%) and effectively projected bounding boxes, covering 89.8% of manually annotated boxes with 87.5% of projections achieving an Intersection over Union (IoU) greater than 0.5. Trait values extracted from predicted bounding instances showed high agreement with manual annotations (r = 0.87-0.97, IoU >= 0.4). Detection outputs were reused across time points to extract plant height and Normalized Difference Vegetation Index with minimal additional annotation, facilitating efficient temporal phenotyping. By combining modular design, reproducibility, and geospatial precision, MatchPlant offers a scalable framework for UAV-based plant-level analysis with broad applicability in agricultural and environmental monitoring.
Code (1)
Tasks
object-detectionObject DetectionSimilar Papers 제목 키워드 기반
Accurate and versatile 3D segmentation of plant tissues at cellular resolution
Quantitative analysis of plant and animal morphogenesis requires accurate segmentation of individual cells in volumetric images of growing organs. In the last years, deep learning has provided robust automated algorithms…
Cell Segmentationgraph partitioningSegmentationSimultaneously Predicting Multiple Plant Traits from Multiple Sensors via Deformable CNN Regression
Trait measurement is critical for the plant breeding and agricultural production pipeline. Typically, a suite of plant traits is measured using laborious manual measurements and then used to train and/or validate higher …
regressionPlantExpertVQA: A Visual Question Answering Dataset for Benchmarking Vision-Language Models in Plant Science
Existing plant-disease datasets target classification and detection, leaving vision-language models unable to support interactive, reasoning-based diagnosis. To address this, we present PlantExpertVQA, a large-scale visu…
parameter-efficient fine-tuningVisual Question AnsweringDomain AdaptationPlantMarkerBench: A Multi-Species Benchmark for Evidence-Grounded Plant Marker Reasoning
Cell-type-specific marker genes are fundamental to plant biology, yet existing resources primarily rely on curated databases or high-throughput studies without explicitly modeling the supporting evidence found in scienti…
Information ExtractionMulti-Scale ViT Inference with Habitat-Fit Priors and kNN Retrieval for Multi-Species Plant Identification
This paper describes DS@GT ARC's third-place solution to the PlantCLEF 2026 challenge on multi-species plant identification in vegetation quadrat images, where systems must predict every species present in high-resolutio…