Skip to main content
Advertisement
Browse Subject Areas
?

Click through the PLOS taxonomy to find articles in your field.

For more information about PLOS Subject Areas, click here.

< Back to Article

Fig 1.

Overview of canola silique segmentation and counting.

(A) Sparse reconstruction. (B) Dense reconstruction. (C) Point cloud preprocessing. (D) Point cloud augmentation. (E) Segmentation model prediction result. (F) Segmented Silique Point Cloud. (G) Silique instance clustering result.

More »

Fig 1 Expand

Fig 2.

Imaging platform.

More »

Fig 2 Expand

Table 1.

Rapeseed video acquisition and image processing data protocol.

More »

Table 1 Expand

Fig 3.

Reconstructed canola point cloud samples.

More »

Fig 3 Expand

Fig 4.

KAN-GLNet network model.

More »

Fig 4 Expand

Fig 5.

The overall architecture of KGL-PointNet and its core components.

(A) The complete network structure of KGL-PointNet. (B) The multi-scale feature enhancement module, GLS Attention. (C) The feedforward network based on partial convolution, PCFN.

More »

Fig 5 Expand

Fig 6.

Network architecture diagrams of Kolmogorov-Arnold, FastKAN, and reverse bottleneck KAN convolutions.

(A) Kolmogorov-Arnold and FastKAN Convolutions. (B) Reverse Bottleneck KAN Convolutions.

More »

Fig 6 Expand

Fig 7.

Network architecture diagrams of the GS attention module and the LS attention module.

(A) GS Attention module structure. (B) LS Attention module structure.

More »

Fig 7 Expand

Table 2.

Definitions of evaluation metrics used for semantic segmentation and clustering.

More »

Table 2 Expand

Table 3.

Hardware and software specifications.

More »

Table 3 Expand

Fig 8.

Training loss and accuracy curves of KAN-GLNet.

More »

Fig 8 Expand

Table 4.

A comparison of semantic segmentation performance across five networks, with the top results highlighted in bold.

More »

Table 4 Expand

Fig 9.

KAN-GLNet and baseline models segmentation visualization on test set.

More »

Fig 9 Expand

Table 5.

Comparison between the actual number and the detected number of canola siliques.

More »

Table 5 Expand

Table 6.

Ablation experiments on KAN-GLNet were conducted using different modules and combinations on the testing set.

More »

Table 6 Expand

Table 7.

Comparison of segmentation accuracy and parameter count between Kolmogorov-Arnold convolutions, FastKAN convolutions, reverse bottleneck KAN convolutions, and the baseline model.

More »

Table 7 Expand

Table 8.

Comparison of reverse bottleneck KAN convolutions replacing single-layer and multi-layer convolutions (Conv).

More »

Table 8 Expand

Fig 10.

DBSCAN hyperparameter search.

(A) Impact of varying parameters on clustering performance (ground truth silique count: 78). (B) Impact of varying parameters on clustering performance (ground truth silique count: 144).

More »

Fig 10 Expand

Fig 11.

Comparison of DBSCAN clustering with and without SOR filtering.

(A) Original silique labels. (B) Clustering result using DBSCAN. (C) Clustering result using DBSCAN with SOR filtering.

More »

Fig 11 Expand

Fig 12.

Canola experimental field at Sichuan Agricultural University, Ya’an City, Sichuan Province, China.

More »

Fig 12 Expand