Deep Segmentation of Point Clouds of Wheat

Ghahremani, Morteza; Williams, Kevin; Corke, Fiona; Tiddeman, Bernard; Liu, Yonghuai; Doonan, John

doi:10.3389/fpls.2021.608732

Cited by 25 publications

(12 citation statements)

References 61 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The difference in temperature between wheat ears and other parts of the plant is used to segment the ears and delineate the color threshold for counting ( Fernandez-Gallego et al, 2019 ). With the development of 3D technology and the popularity of 3D devices, 3D technology has also been applied to wheat-ear identification ( Velumani, 2017 ; Ghahremani et al, 2021 ), using 3D laser point cloud segmentation technology to achieve wheat-ear identification, which provides another new idea for wheat-ear counting.…”

Section: Discussionmentioning

confidence: 99%

Rapid Detection of Wheat Ears in Orthophotos From Unmanned Aerial Vehicles in Fields Based on YOLOX

et al. 2022

View full text Add to dashboard Cite

Wheat ears in unmanned aerial vehicles (UAV) orthophotos are characterized by occlusion, small targets, dense distribution, and complex backgrounds. Rapid identification of wheat ears in UAV orthophotos in a field environment is critical for wheat yield prediction. Three improvements were achieved based on YOLOX-m: mosaic optimized, using BiFPN structure, and attention mechanism, then ablation experiments were performed to verify the effect of each improvement. Three scene datasets were established: images were acquired during three different growing periods, at three planting densities, and under three scenarios of UAV flight heights. In ablation experiments, three improvements had increased recognition accuracies on the experimental dataset. Compared the accuracy of the standard model with our improved model on three scene datasets. Our improved model during three different periods, at three planting densities, and under three scenarios of the UAV flight height, obtaining 88.03%, 87.59%, and 87.93% accuracies, which were, respectively, 2.54%, 1.89%, and 2.15% better than the original model. The results of this study showed that the improved YOLOX-m model can achieve UAV orthophoto wheat recognition under different practical scenarios in large fields, and that the best combination were obtained images from the wheat milk stage, low planting density, and low flight altitude.

show abstract

Section: Discussionmentioning

confidence: 99%

Rapid Detection of Wheat Ears in Orthophotos From Unmanned Aerial Vehicles in Fields Based on YOLOX

et al. 2022

View full text Add to dashboard Cite

show abstract

“…The experimental results show that, compared with previous methods, our method has competitive advantage in the 3D reconstruction of plants, both in terms of speed and quality. Future work will focus on more demanding tasks such as the instance segmentation of organs or other features from the 3D reconstructions, with a view to extracting quantitative trait information from genetically informative populations of crop plants as described in [19].…”

Section: Discussionmentioning

confidence: 99%

Fast and Accurate 3D Reconstruction of Plants Using MVSNet and Multi-View Images

Chen

Lou

et al. 2021

Advances in Intelligent Systems and Computing

Self Cite

View full text Add to dashboard Cite

Accurate 3D reconstruction of morphological structures, growth processes is a prerequisite for image-based measurement of biological organisms. It is a particular challenge for digital plant and crop research. In this paper, multi-view images of structurally very different plants including Arabidopsis, Wheat and Physalis, were taken with a consumer-grade digital camera with a zoom lens and a turntable. Camera parameters were estimated using the SfM method (COLMAP), and then 3D point clouds were reconstructed using MVSNet and the camera parameters. The results show that the proposed method is able to quickly produce denser and complete 3D point cloud of plants. Compared with the existing methods, our method is an end-to-end framework and is more automatic and more promising for dense 3D reconstruction of plants, especially for plant phenotyping.

show abstract

“…Compared with 2D imaging, 3D imaging techniques allow point cloud acquisition of plants, from which many more spatial and volumetric traits during plant growth can be calculated accurately (Wu et al, 2022). In fact, 3D imaging technologies are the most popular methods to analyze the structure of plants and organs (Ghahremani et al, 2021). Current 3D imaging techniques mainly include image-based, laser scanning-based, and depth camera-based techniques.…”

Section: Introductionmentioning

confidence: 99%

Dynamic detection of three-dimensional crop phenotypes based on a consumer-grade RGB-D camera

Peng

Li²,

Meng³

et al. 2023

Front. Plant Sci.

View full text Add to dashboard Cite

IntroductionNondestructive detection of crop phenotypic traits in the field is very important for crop breeding. Ground-based mobile platforms equipped with sensors can efficiently and accurately obtain crop phenotypic traits. In this study, we propose a dynamic 3D data acquisition method in the field suitable for various crops by using a consumer-grade RGB-D camera installed on a ground-based movable platform, which can collect RGB images as well as depth images of crop canopy sequences dynamically.MethodsA scale-invariant feature transform (SIFT) operator was used to detect adjacent date frames acquired by the RGB-D camera to calculate the point cloud alignment coarse matching matrix and the displacement distance of adjacent images. The data frames used for point cloud matching were selected according to the calculated displacement distance. Then, the colored ICP (iterative closest point) algorithm was used to determine the fine matching matrix and generate point clouds of the crop row. The clustering method was applied to segment the point cloud of each plant from the crop row point cloud, and 3D phenotypic traits, including plant height, leaf area and projected area of individual plants, were measured.Results and DiscussionWe compared the effects of LIDAR and image-based 3D reconstruction methods, and experiments were carried out on corn, tobacco, cottons and Bletilla striata in the seedling stage. The results show that the measurements of the plant height (R²= 0.9~0.96, RSME = 0.015~0.023 m), leaf area (R²= 0.8~0.86, RSME = 0.0011~0.0041 m2 ) and projected area (R² = 0.96~0.99) have strong correlations with the manual measurement results. Additionally, 3D reconstruction results with different moving speeds and times throughout the day and in different scenes were also verified. The results show that the method can be applied to dynamic detection with a moving speed up to 0.6 m/s and can achieve acceptable detection results in the daytime, as well as at night. Thus, the proposed method can improve the efficiency of individual crop 3D point cloud data extraction with acceptable accuracy, which is a feasible solution for crop seedling 3D phenotyping outdoors.

show abstract

Deep Segmentation of Point Clouds of Wheat

Cited by 25 publications

References 61 publications

Rapid Detection of Wheat Ears in Orthophotos From Unmanned Aerial Vehicles in Fields Based on YOLOX

Rapid Detection of Wheat Ears in Orthophotos From Unmanned Aerial Vehicles in Fields Based on YOLOX

Fast and Accurate 3D Reconstruction of Plants Using MVSNet and Multi-View Images

Dynamic detection of three-dimensional crop phenotypes based on a consumer-grade RGB-D camera

Contact Info

Product

Resources

About