Figure 5 - available via license: Creative Commons Attribution 4.0 International
Content may be subject to copyright.
Download
View publication
Visualization comparison of feature maps in backbone networks between PSPNet and CBAM-PSPNet. (a) PSPNet. (b) CBAM-PSPNet.

Visualization comparison of feature maps in backbone networks between PSPNet and CBAM-PSPNet. (a) PSPNet. (b) CBAM-PSPNet.

Source publication
Figure 1. Flowchart of the stereovision-based anthropometric system.
Figure 5. Visualization comparison of feature maps in backbone networks...
Figure 6. Structural chart of the residual block from the common...
Figure 7. Schematic diagram of CBAM-PSPNet.
+10 Figure 8. Schematic diagram of the refined stereo matching at sub-pixel...
An Improved Human-Body-Segmentation Algorithm with Attention-Based Feature Fusion and a Refined Stereo-Matching Scheme Working at the Sub-Pixel Level for the Anthropometric System
Article
Full-text available
  • Nov 2022
This paper proposes an improved human-body-segmentation algorithm with attention-based feature fusion and a refined corner-based feature-point design with sub-pixel stereo matching for the anthropometric system. In the human-body-segmentation algorithm, four CBAMs are embedded in the four middle convolution layers of the backbone network (ResNet101...
Cite
Download full-text

Context in source publication

Context 1
... CBAM is embedded in the output of each of the four layers. Figure 5 shows the visualization comparison of feature maps between the backbone network of PSPNet and that of CBAM-PSPNet. The visualization of six feature maps in the feature extraction stage is compared, corresponding to the outputs of Conv1, MaxPool, Layer1, Layer2, Layer3 and Layer4 in Figure 4. ...