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.

Comparison of parameters and cost of different detection models.

(a) Model Parameters. (b) Computational Cost (FLOPs).

More »

Fig 1 Expand

Fig 2.

The structure of the proposed DOLD-Net model.

The DBOAN backbone extracts hierarchical multi-scale features (B2–B5), the CGFP integrates and fuses them through the CSFE, FSAM, and CAOFM to generate the feature pyramid (P2–P5), and the Decoder performs object classification and bounding box prediction.

More »

Fig 2 Expand

Fig 3.

The structure of DBOB.

More »

Fig 3 Expand

Fig 4.

The structure of CSFE.

More »

Fig 4 Expand

Fig 5.

The structure of SS2D.

Image sourced from [20] under the French Open License 2.0 license.

More »

Fig 5 Expand

Fig 6.

The structure of FSAM.

More »

Fig 6 Expand

Fig 7.

The structure of CAOFM.

More »

Fig 7 Expand

Table 1.

Performance comparison of different models on the dataset.

More »

Table 1 Expand

Table 2.

Performance comparison of different models on the dataset.

More »

Table 2 Expand

Table 3.

Performance comparison of different models on the CherryChèvre dataset.

More »

Table 3 Expand

Table 4.

Performance comparison of different models on the SheepCounter dataset.

More »

Table 4 Expand

Table 5.

Performance comparison of different models on the ChickenFlow dataset.

More »

Table 5 Expand

Table 6.

Ablation results of different modules across various datasets.

More »

Table 6 Expand

Table 7.

Ablation results of different CGFP module components.

More »

Table 7 Expand

Table 8.

Ablation results of different kernel size settings.

More »

Table 8 Expand

Table 9.

Impact of different propagation counts and locations on model performance.

More »

Table 9 Expand

Table 10.

Impact of different fusion methods on the performance of the model.

More »

Table 10 Expand

Table 11.

Impact of different feature extraction modules on the performance of the model.

More »

Table 11 Expand

Table 12.

Comparison of different wavelet decomposition methods in the FSAM module.

More »

Table 12 Expand

Table 13.

Impact of different core operators within the CSFE module on model performance.

More »

Table 13 Expand

Fig 8.

Visual results of different models on the task of livestock detection under dense occlusion.

Green boxes denote correctly detected targets (TP), red boxes denote falsely detected targets (FP), and blue boxes denote missed targets (FN). Images in rows 1, 4, 5 and 8 sourced from [19], available under the CC0 public domain dedication. Images in rows 2 and 6 sourced from [43] under the CC BY 4.0 license. Images in rows 3 and 7 sourced from [3] under the CC BY 4.0 license.

More »

Fig 8 Expand

Fig 9.

Heatmap across different datasets.

Warmer colors indicate stronger model responses or attention, whereas cooler colors indicate weaker responses. Images in rows 1, 2 and 3 sourced from [19], available under the CC0 public domain dedication. Images in rows 4 sourced from [3] under a CC BY 4.0 license. Images in rows 5 and 6 sourced from [43] under the CC BY 4.0 license.

More »

Fig 9 Expand

Fig 10.

Feature map heatmaps with and without CSFE.

Image sourced from [19], available under the CC0 public domain dedication.

More »

Fig 10 Expand

Fig 11.

Failure case of DOLD-Net under complex pose conditions.

Image sourced from [19], available under the CC0 public domain dedication.

More »

Fig 11 Expand

Fig 12.

Comparison of 1D Semantic Sequence Unrolling between Normal and Extreme Poses.

Image sourced from [19], available under the CC0 public domain dedication.

More »

Fig 12 Expand