Segment Any Leaf 3D: A Zero-Shot 3D Leaf Instance Segmentation Method Based on Multi-View Images

Exploring the relationships between plant phenotypes and genetic information requires advanced phenotypic analysis techniques for precise characterization. However, the diversity and variability of plant morphology challenge existing methods, which often fail to generalize across species and require...

Full description

Saved in:
Bibliographic Details
Main Authors: Yunlong Wang, Zhiyong Zhang
Format: Article
Language:English
Published: MDPI AG 2025-01-01
Series:Sensors
Subjects:
Online Access:https://www.mdpi.com/1424-8220/25/2/526
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1832587517526802432
author Yunlong Wang
Zhiyong Zhang
author_facet Yunlong Wang
Zhiyong Zhang
author_sort Yunlong Wang
collection DOAJ
description Exploring the relationships between plant phenotypes and genetic information requires advanced phenotypic analysis techniques for precise characterization. However, the diversity and variability of plant morphology challenge existing methods, which often fail to generalize across species and require extensive annotated data, especially for 3D datasets. This paper proposes a zero-shot 3D leaf instance segmentation method using RGB sensors. It extends the 2D segmentation model SAM (Segment Anything Model) to 3D through a multi-view strategy. RGB image sequences captured from multiple viewpoints are used to reconstruct 3D plant point clouds via multi-view stereo. HQ-SAM (High-Quality Segment Anything Model) segments leaves in 2D, and the segmentation is mapped to the 3D point cloud. An incremental fusion method based on confidence scores aggregates results from different views into a final output. Evaluated on a custom peanut seedling dataset, the method achieved point-level precision, recall, and F1 scores over 0.9 and object-level mIoU and precision above 0.75 under two IoU thresholds. The results show that the method achieves state-of-the-art segmentation quality while offering zero-shot capability and generalizability, demonstrating significant potential in plant phenotyping.
format Article
id doaj-art-a5402682a11740c2b589d4705b79b503
institution Kabale University
issn 1424-8220
language English
publishDate 2025-01-01
publisher MDPI AG
record_format Article
series Sensors
spelling doaj-art-a5402682a11740c2b589d4705b79b5032025-01-24T13:49:13ZengMDPI AGSensors1424-82202025-01-0125252610.3390/s25020526Segment Any Leaf 3D: A Zero-Shot 3D Leaf Instance Segmentation Method Based on Multi-View ImagesYunlong Wang0Zhiyong Zhang1School of Electronic and Communication Engineering, Sun Yat-sen University, Shenzhen 518000, ChinaSchool of Electronic and Communication Engineering, Sun Yat-sen University, Shenzhen 518000, ChinaExploring the relationships between plant phenotypes and genetic information requires advanced phenotypic analysis techniques for precise characterization. However, the diversity and variability of plant morphology challenge existing methods, which often fail to generalize across species and require extensive annotated data, especially for 3D datasets. This paper proposes a zero-shot 3D leaf instance segmentation method using RGB sensors. It extends the 2D segmentation model SAM (Segment Anything Model) to 3D through a multi-view strategy. RGB image sequences captured from multiple viewpoints are used to reconstruct 3D plant point clouds via multi-view stereo. HQ-SAM (High-Quality Segment Anything Model) segments leaves in 2D, and the segmentation is mapped to the 3D point cloud. An incremental fusion method based on confidence scores aggregates results from different views into a final output. Evaluated on a custom peanut seedling dataset, the method achieved point-level precision, recall, and F1 scores over 0.9 and object-level mIoU and precision above 0.75 under two IoU thresholds. The results show that the method achieves state-of-the-art segmentation quality while offering zero-shot capability and generalizability, demonstrating significant potential in plant phenotyping.https://www.mdpi.com/1424-8220/25/2/526plant phenotypinginstance segmentationRGB sensorszero-shot segmentationmulti-view stereo
spellingShingle Yunlong Wang
Zhiyong Zhang
Segment Any Leaf 3D: A Zero-Shot 3D Leaf Instance Segmentation Method Based on Multi-View Images
Sensors
plant phenotyping
instance segmentation
RGB sensors
zero-shot segmentation
multi-view stereo
title Segment Any Leaf 3D: A Zero-Shot 3D Leaf Instance Segmentation Method Based on Multi-View Images
title_full Segment Any Leaf 3D: A Zero-Shot 3D Leaf Instance Segmentation Method Based on Multi-View Images
title_fullStr Segment Any Leaf 3D: A Zero-Shot 3D Leaf Instance Segmentation Method Based on Multi-View Images
title_full_unstemmed Segment Any Leaf 3D: A Zero-Shot 3D Leaf Instance Segmentation Method Based on Multi-View Images
title_short Segment Any Leaf 3D: A Zero-Shot 3D Leaf Instance Segmentation Method Based on Multi-View Images
title_sort segment any leaf 3d a zero shot 3d leaf instance segmentation method based on multi view images
topic plant phenotyping
instance segmentation
RGB sensors
zero-shot segmentation
multi-view stereo
url https://www.mdpi.com/1424-8220/25/2/526
work_keys_str_mv AT yunlongwang segmentanyleaf3dazeroshot3dleafinstancesegmentationmethodbasedonmultiviewimages
AT zhiyongzhang segmentanyleaf3dazeroshot3dleafinstancesegmentationmethodbasedonmultiviewimages