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.

Parturition data collection.

More »

Fig 1 Expand

Fig 2.

Display of image enhancement effect.

More »

Fig 2 Expand

Table 1.

Equine parturition dataset.

More »

Table 1 Expand

Table 2.

Test set labelling details.

More »

Table 2 Expand

Fig 3.

CBAM module architecture.

The upper part of the CBAM architecture consists of two components: the channel attention module and the spatial attention module. These modules are applied to the input feature map, and the output is obtained by element-wise multiplication with the input feature map. The lower part shows the specific placement of the CBAM module in ResNet101, where it is added at the end of each residual unit in the third and fourth stages.

More »

Fig 3 Expand

Fig 4.

CARAFE-BFP Module.

The input feature maps come from the outputs of the FPN, namely P2’, P3’, P4’, and P5’. These feature maps are processed through the Integrate and Refine operations to generate new feature maps P2, P3, P4, and P5, which are used for subsequent object detection tasks.

More »

Fig 4 Expand

Fig 5.

GRoIE Module.

More »

Fig 5 Expand

Fig 6.

L-MPD network architecture.

More »

Fig 6 Expand

Table 3.

Experimental parameter setting.

More »

Table 3 Expand

Table 4.

Evaluation results of Libra R-CNN with different backbone networks.

More »

Table 4 Expand

Table 5.

Ablation experiment.

More »

Table 5 Expand

Fig 7.

Performance evaluation and training process analysis for key components in ablation study.

More »

Fig 7 Expand

Table 6.

Comparison of recognition of standing and lateral recumbent parturition in mare.

More »

Table 6 Expand

Table 7.

Different object detection algorithm performance comparison.

More »

Table 7 Expand

Fig 8.

Mare parturition identification under video stream continuous monitoring scenarios.

More »

Fig 8 Expand

Table 8.

Ten-fold cross-validation.

More »

Table 8 Expand

Fig 9.

Category activation mapping.

More »

Fig 9 Expand

Fig 10.

Examples of recognition errors.

(a) misidentification due to insufficient lighting, (b) indistinct features due to camera angle and capture range, (c) intrusive interference, (d) tail occlusion, (e) non-parturition mares misidentified as parturition mares due to environmental interference.

More »

Fig 10 Expand