High-Resolution Plant Shape Measurements from Multi-view Stereo Reconstruction

Klodt, Maria; Cremers, Daniel

doi:10.1007/978-3-319-16220-1_13

Cited by 19 publications

(37 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Surprisingly, the main performance gain potential does currently not lie in using more sophisticated reconstruction methods allowing for higher achievable voxel resolutions R, e.g. achievable by [23] and necessary for reconstruction of more complex surfaces. Reducing preprocessing and transfer times by reducing image number N and pixel resolution seems more promising.…”

Section: Discussionmentioning

confidence: 99%

See 1 more Smart Citation

3D Surface Reconstruction of Plant Seeds by Volume Carving

Roussel¹,

Fischbach²,

Jahnke³

et al. 2015

Procedings of the Proceedings of the Computer Vision Problems in Plant Phenotyping Workshop 2015

View full text Add to dashboard Cite

We describe a method for 3D reconstruction of plant seed surfaces, focusing on small seeds with diameters as small as 200 µm. The method considers robotized systems allowing single seed handling in order to rotate a single seed in front of a camera. Even though such systems feature high position repeatability, at sub-millimeter object scales, camera pose variations have to be compensated. We do this by robustly estimating the tool center point from each acquired image. 3D reconstruction can then be performed by a simple shape-from-silhouette approach. In experiments we investigate runtimes, the achieved accuracy, and show as a proof of principle that the proposed method is well sufficient for 3D seed phenotyping purposes.

show abstract

Section: Discussionmentioning

confidence: 99%

“…Even higher resolutions become available on current desktop computer hardware, when hierarchically representing the voxel grid, e.g. as an octree [23].…”

Section: Reconstructing Seed Shape From Silhouettesmentioning

confidence: 99%

3D Surface Reconstruction of Plant Seeds by Volume Carving

Roussel¹,

Fischbach²,

Jahnke³

et al. 2015

Procedings of the Proceedings of the Computer Vision Problems in Plant Phenotyping Workshop 2015

View full text Add to dashboard Cite

show abstract

“…We ran the reconstruction pipeline on hundreds of plants and it would be difficult to verify the accuracy of each plant manually. Inspired by the work of Klodt and Cremers (2015), we computed the Dice coefficient denoted by D and used it to verify whether a plant was successfully reconstructed without visually inspecting it. We re-project all voxels from each plant to the six views and we then compute D between the re-projected images and the plant masks obtained a) b) c)…”

Section: D Reconstruction Accuracymentioning

confidence: 99%

“…Space carving is suitable to phenotyping facilities because the environment is controlled, which eases calibration and segmentation. Recent contributions focus on seedlings, which are smaller plants that are easier to reconstruct (Koenderink et al, 2009;Klodt and Cremers, 2015;Golbach et al, 2016). Other contributions focus on accelerating voxel carving with octrees (Scharr et al, 2017).…”

Section: Introductionmentioning

confidence: 99%

Voxel Carving Based 3D Reconstruction of Sorghum Identifies Genetic Determinants of Radiation Interception Efficiency

Gaillard

Miao

Schnable

et al. 2020

Preprint

View full text Add to dashboard Cite

Changes in canopy architecture traits have been shown to contribute to yield increases. Optimizing both light interception and radiation use efficiency of agricultural crop canopies will be essential to meeting growing needs for food. Canopy architecture is inherently 3D, but many approaches to measuring canopy architecture component traits treat the canopy as a two dimensional structure in order to make large scale measurement, selective breeding, and gene identification logistically feasible.We develop a high throughput voxel carving strategy to reconstruct three dimensional representations of maize and sorghum from a small number of RGB photos. This approach was employed to generate three dimensional reconstructions of a sorghum association population at the late vegetative stage of development. Light interception parameters estimated from these reconstructions enabled the identification of both known and previously unreported loci controlling light interception efficiency in sorghum.The approach described here is generalizable and scalable and it enables 3D reconstructions from existing plant high throughput phenotyping datasets.For future datasets we propose a set of best practices to increase the accuracy of three dimensional reconstructions.

show abstract

“…Watanabe et al [4] used a 3D digitizer to measure rice plant structure to specify rice plant architecture and to find suitable functions for describing its 3D growth at all stages. Multiple-view stereo imaging was applied to reconstruct 3D models of plants from 2D images [5] and 3D plant models with high spatial resolution were also achieved [6]. However, it has proven to be challenging for stereo vision to handle the complexity of plant canopies given the difficulties in stereo matching caused by leaf occlusion and the lack of leaf surface texture.…”

Section: Introductionmentioning

confidence: 99%

A Robotic Platform for Corn Seedling Morphological Traits Characterization

Lü

Tang

Whitham

et al. 2017

Sensors

View full text Add to dashboard Cite

Crop breeding plays an important role in modern agriculture, improving plant performance, and increasing yield. Identifying the genes that are responsible for beneficial traits greatly facilitates plant breeding efforts for increasing crop production. However, associating genes and their functions with agronomic traits requires researchers to observe, measure, record, and analyze phenotypes of large numbers of plants, a repetitive and error-prone job if performed manually. An automated seedling phenotyping system aimed at replacing manual measurement, reducing sampling time, and increasing the allowable work time is thus highly valuable. Toward this goal, we developed an automated corn seedling phenotyping platform based on a time-of-flight of light (ToF) camera and an industrial robot arm. A ToF camera is mounted on the end effector of the robot arm. The arm positions the ToF camera at different viewpoints for acquiring 3D point cloud data. A camera-to-arm transformation matrix was calculated using a hand-eye calibration procedure and applied to transfer different viewpoints into an arm-based coordinate frame. Point cloud data filters were developed to remove the noise in the background and in the merged seedling point clouds. A 3D-to-2D projection and an x-axis pixel density distribution method were used to segment the stem and leaves. Finally, separated leaves were fitted with 3D curves for morphological traits characterization. This platform was tested on a sample of 60 corn plants at their early growth stages with between two to five leaves. The error ratios of the stem height and leave length measurements are 13.7% and 13.1%, respectively, demonstrating the feasibility of this robotic system for automated corn seedling phenotyping.

show abstract

High-Resolution Plant Shape Measurements from Multi-view Stereo Reconstruction

Cited by 19 publications

References 27 publications

3D Surface Reconstruction of Plant Seeds by Volume Carving

3D Surface Reconstruction of Plant Seeds by Volume Carving

Voxel Carving Based 3D Reconstruction of Sorghum Identifies Genetic Determinants of Radiation Interception Efficiency

A Robotic Platform for Corn Seedling Morphological Traits Characterization

Contact Info

Product

Resources

About