Canopy Volume Extraction of Citrus reticulate Blanco cv. Shatangju Trees Using UAV Image-Based Point Cloud Deep Learning

Qi, Yuan; Dong, Xuhua; Chen, Pengchao; Lee, Kyeong–Hwan; Lan, Yubin; Lu, Xiaoyang; Jia, Ruichang; Deng, Jizhong; Zhang, Yali

doi:10.3390/rs13173437

Cited by 20 publications

(12 citation statements)

References 48 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In this research, UAV, MA and MLS point clouds were compared to assess the canopy size parameters of vertical trained vines (Vitis vinifera L.). Manual measurements of the canopy volumes were not taken due to several uncertainties, such as the identification of the vine canopy boundary and being subjective and dependent on the person taking the measure itself as well as on the tool or strategy used to assess the canopy height and thickness [60,61]. Moreover, some researchers have found that manual measurements over-estimate the canopy thickness of about 30% with respect to LiDAR ones [62].…”

Section: Discussionmentioning

confidence: 99%

“…UAV technology was widely used to assess canopy volumes and it was shown to be a quick and low-cost solution compared to ground measurements of canopy size parameters [50, 60,[64][65][66][67][68][69]. The UAV point cloud processing led to similar results in canopy volume values concerning other research, but they used a voxel method [70] and an alphashape approach [38,71].…”

Section: Discussionmentioning

confidence: 99%

See 1 more Smart Citation

Comparison of Aerial and Ground 3D Point Clouds for Canopy Size Assessment in Precision Viticulture

et al. 2022

View full text Add to dashboard Cite

In precision viticulture, the intra-field spatial variability characterization is a crucial step to efficiently use natural resources by lowering the environmental impact. In recent years, technologies such as Unmanned Aerial Vehicles (UAVs), Mobile Laser Scanners (MLS), multispectral sensors, Mobile Apps (MA) and Structure from Motion (SfM) techniques enabled the possibility to characterize this variability with low efforts. The study aims to evaluate, compare and cross-validate the potentiality and the limits of several tools (UAV, MA, MLS) to assess the vine canopy size parameters (thickness, height, volume) by processing 3D point clouds. Three trials were carried out to test the different tools in a vineyard located in the Chianti Classico area (Tuscany, Italy). Each test was made of a UAV flight, an MLS scanning over the vineyard and a MA acquisition over 48 geo-referenced vines. The Leaf Area Index (LAI) were also assessed and taken as reference value. The results showed that the analyzed tools were able to correctly discriminate between zones with different canopy size characteristics. In particular, the R2 between the canopy volumes acquired with the different tools was higher than 0.7, being the highest value of R2 = 0.78 with a RMSE = 0.057 m3 for the UAV vs. MLS comparison. The highest correlations were found between the height data, being the highest value of R2 = 0.86 with a RMSE = 0.105 m for the MA vs. MLS comparison. For the thickness data, the correlations were weaker, being the lowest value of R2 = 0.48 with a RMSE = 0.052 m for the UAV vs. MLS comparison. The correlation between the LAI and the canopy volumes was moderately strong for all the tools with the highest value of R2 = 0.74 for the LAI vs. V_MLS data and the lowest value of R2 = 0.69 for the LAI vs. V_UAV data.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Discussionmentioning

confidence: 99%

Comparison of Aerial and Ground 3D Point Clouds for Canopy Size Assessment in Precision Viticulture

et al. 2022

View full text Add to dashboard Cite

show abstract

“…A considerable amount of research on orchard canopy information focus on the identification and counting of individual trees ( Morales et al., 2018 ; Cheng et al., 2020 ; Qi et al., 2021 ). In fact, due to geometric features of plant canopies can offer relevant indicators, individual canopy-related features interested farmers but the most accurate estimations for canopies all mostly based on destructive and costly labour-intensive manual measurements ( Gower et al., 1999 ; Jonckheere et al., 2004 ; Ma et al., 2017 ).…”

Section: Introductionmentioning

confidence: 99%

Automatic instance segmentation of orchard canopy in unmanned aerial vehicle imagery using deep learning

Zhang

Chen

et al. 2022

Front. Plant Sci.

View full text Add to dashboard Cite

The widespread use of unmanned aerial vehicles (UAV) is significant for the effective management of orchards in the context of precision agriculture. To reduce the traditional mode of continuous spraying, variable target spraying machines require detailed information about tree canopy. Although deep learning methods have been widely used in the fields of identifying individual trees, there are still phenomena of branches extending and shadows preventing segmenting edges of tree canopy precisely. Hence, a methodology (MPAPR R-CNN) for the high-precision segment method of apple trees in high-density cultivation orchards by low-altitude visible light images captured is proposed. Mask R-CNN with a path augmentation feature pyramid network (PAFPN) and PointRend algorithm was used as the base segmentation algorithm to output the precise boundaries of the apple tree canopy, which addresses the over- and under-sampling issues encountered in the pixel labeling tasks. The proposed method was tested on another miniature map of the orchard. The average precision (AP) was selected to evaluate the metric of the proposed model. The results showed that with the help of training with the PAFPN and PointRend backbone head that AP_seg and AP_box score improved by 8.96% and 8.37%, respectively. It can be concluded that our algorithm could better capture features of the canopy edges, it could improve the accuracy of the edges of canopy segmentation results.

show abstract

“…Apple trees are cultivated worldwide and more than 87 million tons of apples are produced each year (FAOSTAT, 2019). Fertile planting land and high-quality orchard management are necessary to ensure the stable and increased production of apples (Qi et al, 2021). The volume and exterior structure of the canopy of apple trees are significant markers for determining their growth and biological characteristics (Wang et al, 2004).…”

Section: Introductionmentioning

confidence: 99%

“…Gülci (2019) built a 3D canopy model using UAV-based photogrammetry technology to estimate the number, height, and canopy coverage of trees. Based on oblique photogrammetry, Qi et al (2021) combined deep learning-based segmentation to obtain the 3D point cloud of a single fruit tree and estimated the volume of the tree canopy. UAV-based oblique photogrammetry with point cloud data processing has become the most popular method for estimating individual tree volume.…”

Section: Introductionmentioning

confidence: 99%

Drone-Based Three-Dimensional Photogrammetry and Concave Hull by Slices Algorithm for Apple Tree Volume Mapping

2021

Self Cite

View full text Add to dashboard Cite

Purpose Apple tree volume is an important factor in apple quality control and spraying strategies. The measurement is a laborious task because of the complex structure of the apple tree. This study developed a technology for accurately estimating the apple tree volume from unmanned aerial vehicle-based multi-view three-dimensional reconstruction data using a novel concave hull by slices algorithm. Method The CloudCompare software was used to preprocess the 3D data and extract a single tree. The 3D point cloud data of the tree were divided into truncated cone-type small slices of a specific thickness. The area of each slice was calculated using the proposed concave hull by slices algorithm. The tree volume was calculated by summing the volume of slices. The proposed method was verified on ten apple trees by comparing the results obtained using the proposed method with those calculated by two existing methods. ResultsThe proposed method provided the most accurate tree volume, while avoiding the influence of gaps and holes in the tree. The mean absolute percentage error (MAPE) and root mean squared error (RMSE) were 8.07% and 0.55 m 3 , respectively. Conclusion These results indicate that the concave hull by slices method can be used to calculate the tree volume from 3D point cloud data more effectively. Tree volume mapping was achieved by combining the tree volume with the tree position.

show abstract

Canopy Volume Extraction of Citrus reticulate Blanco cv. Shatangju Trees Using UAV Image-Based Point Cloud Deep Learning

Cited by 20 publications

References 48 publications

Comparison of Aerial and Ground 3D Point Clouds for Canopy Size Assessment in Precision Viticulture

Comparison of Aerial and Ground 3D Point Clouds for Canopy Size Assessment in Precision Viticulture

Automatic instance segmentation of orchard canopy in unmanned aerial vehicle imagery using deep learning

Drone-Based Three-Dimensional Photogrammetry and Concave Hull by Slices Algorithm for Apple Tree Volume Mapping

Contact Info

Product

Resources

About