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.

AP comparisons of single-modal and multimodal models at different point cloud resolutions.

More »

Fig 1 Expand

Fig 2.

Delay comparisons of single-modal and multimodal models at different point cloud resolutions.

More »

Fig 2 Expand

Table 1.

The value of AP corresponding to different image resolutions.

More »

Table 1 Expand

Table 2.

Difference between our scheme and the most relevant schemes.

More »

Table 2 Expand

Fig 3.

Edge-assist framework of 3D object detection.

More »

Fig 3 Expand

Fig 4.

Data size of different point cloud resolutions.

More »

Fig 4 Expand

Fig 5.

AP values for single-modal and multimodal models.

More »

Fig 5 Expand

Fig 6.

Delay values for single-modal and multimodal models.

More »

Fig 6 Expand

Fig 7.

AP values of single-modal.

More »

Fig 7 Expand

Fig 8.

Delay values of single-modal.

More »

Fig 8 Expand

Table 3.

Main symbols and definitions.

More »

Table 3 Expand

Fig 9.

Performance comparison under different confidence thresholds.

More »

Fig 9 Expand

Fig 10.

Performance under fixed point resolution and confidence thresholds.

More »

Fig 10 Expand

Fig 11.

The value of terminal single-modal model (PointPillar) of the mapping function between the confidence and AP.

More »

Fig 11 Expand

Fig 12.

The value of the edge multimodal model (DeepInteraction) of the mapping function between the confidence and AP.

More »

Fig 12 Expand

Table 4.

Algorithm 1: Dynamic threshold updating algorithm.

More »

Table 4 Expand

Table 5.

Algorithm 3: Adaptive offloading algorithm.

More »

Table 5 Expand

Fig 13.

The testbed of system.

More »

Fig 13 Expand

Table 6.

Comparison of equipment parameters.

More »

Table 6 Expand

Fig 14.

Transmission rate variation under different time epochs.

More »

Fig 14 Expand

Fig 15.

Performance under different values of.

More »

Fig 15 Expand

Fig 16.

Delay values of different algorithms.

More »

Fig 16 Expand

Fig 17.

AP values of different algorithms.

More »

Fig 17 Expand

Fig 18.

Delay values of different algorithms(BEVFusion used for edge inference).

More »

Fig 18 Expand

Fig 19.

AP values of different algorithms(BEVFusion used for edge inference).

More »

Fig 19 Expand

Fig 20.

Delay values of different algorithms(TransFusion used for edge inference).

More »

Fig 20 Expand

Fig 21.

AP values of different algorithms(TransFusion used for edge inference).

More »

Fig 21 Expand

Fig 22.

Delay values of different algorithms(BEVFusion_L used for device inference).

More »

Fig 22 Expand

Fig 23.

AP values of different algorithms(BEVFusion_L used for device inference).

More »

Fig 23 Expand

Fig 24.

Delay values of different algorithms(TransFusion_L used for device inference).

More »

Fig 24 Expand

Fig 25.

AP values of different algorithms(TransFusion_L used for device inference).

More »

Fig 25 Expand

Fig 26.

Comparison of AP.

More »

Fig 26 Expand

Fig 27.

Delay values of different datasets(KITTI).

More »

Fig 27 Expand

Fig 28.

AP values of different datasets(KITTI).

More »

Fig 28 Expand

Fig 29.

Performance of different point cloud compression algorithms.

More »

Fig 29 Expand

Fig 30.

Delay values of different bandwidths.

More »

Fig 30 Expand

Fig 31.

AP values of different bandwidths.

More »

Fig 31 Expand