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.

Depicts the LDIE-FDNet architecture.

The Backbone establishes a six-tier feature pyramid for multi-scale extraction, while the Neck employs a dynamic hierarchical fusion pyramid for feature refinement. The Head handles localization and classification, with PIoU Loss enhancing geometric characterization of target morphology and spatial configuration.

More »

Fig 1 Expand

Table 1.

Information flow and computational behavior.

More »

Table 1 Expand

Fig 2.

Low-light image enhancement network based on multichannel Retinex model.

More »

Fig 2 Expand

Fig 3.

Conversion Structure Of GSConv.

More »

Fig 3 Expand

Fig 4.

GSConv_C3k2 structure.

More »

Fig 4 Expand

Fig 5.

DySample structure.

More »

Fig 5 Expand

Fig 6.

Architecture of the SDI module.

For clarity, only the refinement process for the third-level features (l = 3) is depicted. SmoothConv denotes a 3x3 convolution for feature smoothing, and X represents the Hadamard product.

More »

Fig 6 Expand

Fig 7.

PIoU conceptual structure.

More »

Fig 7 Expand

Fig 8.

Driver fatigue recognition system.

More »

Fig 8 Expand

Table 2.

Detailed introduction of YawDD data set.

More »

Table 2 Expand

Table 3.

Details of DMS Datasets.

More »

Table 3 Expand

Table 4.

Ablation experiment of YawDD dataset.

More »

Table 4 Expand

Fig 9.

Model state evaluation on the YawDD dataset.

More »

Fig 9 Expand

Fig 10.

Model state evaluation on the DMS dataset.

More »

Fig 10 Expand

Table 5.

Ablation experiment of DMS data set.

More »

Table 5 Expand

Table 6.

Comparison of different loss functions.

More »

Table 6 Expand

Fig 11.

Actual improvement effect in complex driving scenarios.

More »

Fig 11 Expand

Table 7.

Comparative experiments based on YawDD.

More »

Table 7 Expand

Table 8.

Performance comparison across different hardware platforms on YawDD.

More »

Table 8 Expand

Table 9.

Comparative experiment of DMS.

More »

Table 9 Expand

Table 10.

Performance comparison across different hardware platforms on DMS.

More »

Table 10 Expand