Image-based plant modeling

Quan, Long; Tan, Ping; Zeng, Gang; Liu, Yuan; Wang, Jingdong; Kang, Sing Bing

doi:10.1145/1141911.1141929

Cited by 241 publications

(174 citation statements)

References 17 publications

Supporting

Mentioning

170

Contrasting

Unclassified

Order By: Relevance

“…Kinect Fusion to average sensor data and rapidly reconstruct the plant (Izadi et al, 2011), or the use of a model-based approach to fit a geometric plant model to the acquired points (Quan et al, 2006;Ma et al, 2008). Second, the segmentation procedure will need to be improved to better distinguish leaves that are in contact with one another, to better automatically identify the shoot cylinder of the plant, and to potentially make it applicable to other grass or plant species.…”

Section: Discussionmentioning

confidence: 99%

3D sorghum reconstructions from depth images identify QTL regulating shoot architecture

2016

View full text Add to dashboard Cite

Dissecting the genetic basis of complex traits is aided by frequent and nondestructive measurements. Advances in range imaging technologies enable the rapid acquisition of three-dimensional (3D) data from an imaged scene. A depth camera was used to acquire images of sorghum (Sorghum bicolor), an important grain, forage, and bioenergy crop, at multiple developmental time points from a greenhouse-grown recombinant inbred line population. A semiautomated software pipeline was developed and used to generate segmented, 3D plant reconstructions from the images. Automated measurements made from 3D plant reconstructions identified quantitative trait loci for standard measures of shoot architecture, such as shoot height, leaf angle, and leaf length, and for novel composite traits, such as shoot compactness. The phenotypic variability associated with some of the quantitative trait loci displayed differences in temporal prevalence; for example, alleles closely linked with the sorghum Dwarf3 gene, an auxin transporter and pleiotropic regulator of both leaf inclination angle and shoot height, influence leaf angle prior to an effect on shoot height. Furthermore, variability in composite phenotypes that measure overall shoot architecture, such as shoot compactness, is regulated by loci underlying component phenotypes like leaf angle. As such, depth imaging is an economical and rapid method to acquire shoot architecture phenotypes in agriculturally important plants like sorghum to study the genetic basis of complex traits.

show abstract

Section: Discussionmentioning

confidence: 99%

3D sorghum reconstructions from depth images identify QTL regulating shoot architecture

2016

View full text Add to dashboard Cite

show abstract

“…Several authors have dealt with the segmentation of a live plant from background to measure growth using unsupervised [17,25] and semi-supervised methods [36], but not of individual leaves. The use of color in combination with depth images or multiple images for supervised or unsupervised plant segmentation is also common practice [4,10,29,46,49,51,52,57].…”

Section: Related Workmentioning

confidence: 99%

Leaf segmentation in plant phenotyping: a collation study

Scharr

Minervini

French

et al. 2015

Machine Vision and Applications

228

171

View full text Add to dashboard Cite

Image-based plant phenotyping is a growing application domain of computer vision in agriculture. A key task is the segmentation of all individual leaves in images. Here we focus on the most common rosette model plants Arabidopsis and young tobacco. Although leaves do share appearance and shape characteristics, the presence of occlusions and variability in leaf shape and pose, as well as imaging conditions, render this problem challenging. The aim of this paper is to compare several leaf segmentation solutions on a unique and first of its kind dataset containing images from typical phenotyping experiments. In particular, we report and discuss methods and findings of a collection of submissions for the first Leaf Segmentation Challenge (LSC) of the Computer Vision Problems in Plant Phenotyping (CVPPP) workshop in 2014. Four methods are presented: three segment leaves via processing the distance transform in an unsupervised fashion, and the other via optimal template selection and Chamfer matching. Overall, we find that although separating plant from background can be achieved with satisfactory accuracy (>90% Dice score), individual leaf segmentation and counting remain challenging when leaves overlap. Besides, accuracy is lower for younger leaves. We find also that variability in datasets does affect outcomes. Our findings motivate further investigations and development of specialized algorithms for this particular application, and that challenges of this form are ideally suited for advancing the state of the art. Data are publicly available (http://www.plantphenotyping.org/CVPPP2014-dataset) to support future challenges beyond segmentation within this application domain.

show abstract

“…Realistic plants are challenging objects to model and recent advances in automatic modelling can be explained by the convergence of computer graphics and computer vision [8]. We start this state of the art with the first method of plant modelling from images.…”

Section: State Of the Art: Generating Plants From Imagesmentioning

confidence: 99%

“…Quan et al [10,11] and Tan et al [12] also use multiple images to reconstruct a 3D model of trees or plants. In order to avoid the features correspondences in different images, they use views close to each other (more than 20 images for any plants).…”

Section: State Of the Art: Generating Plants From Imagesmentioning

confidence: 99%

Reconstructing Plants in 3D from a Single Image Using Analysis-by-Synthesis

Guénard¹,

Morin²,

Boudon³

et al. 2013

Advances in Visual Computing

View full text Add to dashboard Cite

Abstract. Mature computer vision techniques allow the reconstruction of challenging 3D objects from images. However, due to high complexity of plant topology, dedicated methods for generating 3D plant models must be devised. We propose to generate a 3D model of a plant, using an analysis-by-synthesis method mixing information from a single image and a priori knowledge of the plant species. First, our dedicated skeletonisation algorithm generates a possible branching structure from the foliage segmentation. Then, a 3D generative model, based on a parametric model of branching systems that takes into account botanical knowledge is built. The resulting skeleton follows the hierarchical organisation of natural branching structures. An instance of a 3D model can be generated. Moreover, varying parameter values of the generative model (main branching structure of the plant and foliage), we produce a series of candidate models. The reconstruction is improved by selecting the model among these proposals based on a matching criterion with the image. Realistic results obtained on different species of plants illustrate the performance of the proposed method. Fig. 1. On the left, an original image of Ginkgo tree. In the middle, a possible architecture of the branching extracted with our skeletonisation method. On the right, a 3D model of this tree with the same viewpoint.

show abstract

Image-based plant modeling

Cited by 241 publications

References 17 publications

3D sorghum reconstructions from depth images identify QTL regulating shoot architecture

3D sorghum reconstructions from depth images identify QTL regulating shoot architecture

Leaf segmentation in plant phenotyping: a collation study

Reconstructing Plants in 3D from a Single Image Using Analysis-by-Synthesis

Contact Info

Product

Resources

About