Author Affiliations
1Key Laboratory of Optoelectronic Technology and Systems of Ministry of Education, Chongqing University, Chongqing 400040, China2College of Optoelectronic Engineering, Chongqing University, Chongqing 400040, China3College of Computer and Information Science, Chongqing Normal University, Chongqing 401331, Chinashow less
Fig. 1. RGB-D image semantic segmentation by double-stream weighted Gabor convolution network fusion
Fig. 2. Modulation process of WGoFs
Fig. 3. Convolution process of WGoFs
Fig. 4. Wide residual blocks. (a) Original residual block; (b) wide residual block 1; (c) wide residual block 2
Fig. 5. Architecture of WRN-WGCN module
Fig. 6. Pyramid pooling module
Fig. 7. Proposed pyramid pooling feature fusion module
Fig. 8. RGB and depth images and their corresponding semantic labels in dataset. (a) RGB images; (b) depth images; (c) semantic labels
Fig. 9. Loss curves in training process
Fig. 10. Test accuracy versus number of scales and number of directions. (a) Test accuracy under different number of scales; (b) test accuracy under different number of directions
Fig. 11. Semantic segmentation results obtained by various methods on NYUDv2 dataset. (a) RGB; (b) depth; (c) GT; (d) baseline; (e) WRN-CNN; (f) WGCN; (g) PP-Fusion; (h) FCN; (i) SegNet; (j) ours
Fig. 12. Semantic segmentation results obtained by various methods on SUN-RGBD dataset. (a) RGB; (b) depth; (c) GT; (d) baseline; (e) WRN-CNN; (f) WGCN; (g) PP-Fusion; (h) FCN; (i) SegNet; (j) ours
Group name | Output feature size | Block type |
---|
GCConv1 | N×N | | GCConv2 | N×N | ×L | GCConv3 | N×N | ×L | GCConv4 | (N/2)×(N/2) | ×L |
|
Table 1. Structural parameter setting of WRN-WGCN
Model name | Filter size | Model size /MB |
---|
Model 1 | 5×5 | 163 | Model 2 | 5×5 | 124 | Model 3 | 3×3 | 148 | Model 4 | 3×3 | 117 |
|
Table 2. Model sizes with different filter sizes
Method | Module | Acc /% | mAcc /% | mIoU /% | FWIoU /% |
---|
WRN-CNN | WGCN | PP-Fusion |
---|
Ours | √ | √ | √ | 66.3 | 50.8 | 40.0 | 53.1 | Variant 1 | | | | 58.3 | 41.6 | 30.1 | 45.8 | Variant 2 | √ | | | 58.6 | 42.4 | 31.9 | 45.3 | Variant 3 | | √ | | 60.8 | 48.2 | 35.8 | 50.4 | Variant 4 | | | √ | 63.2 | 45.8 | 36.4 | 46.6 | FCN[2] | | | | 65.4 | 45.1 | 34.3 | 48.6 | SegNet[3] | | | | 56.2 | 47.6 | 35.1 | 50.1 |
|
Table 3. Comparison of results for different segmentation algorithms on NYUDv2 dataset
Method | Module | Acc /% | mAcc /% | mIoU /% | FWIoU /% |
---|
WRN-CNN | WGCN | PP-Fusion |
---|
Ours | √ | √ | √ | 58.2 | 38.5 | 28.2 | 42.0 | Variant 1 | | | | 45.2 | 33.7 | 21.8 | 37.4 | Variant 2 | √ | | | 44.8 | 34.5 | 23.1 | 38.6 | Variant 3 | | √ | | 54.6 | 35.1 | 27.3 | 37.7 | Variant 4 | | | √ | 56.1 | 34.6 | 26.0 | 36.3 | FCN[2] | | | | 49.5 | 36.5 | 23.7 | 35.8 | SegNet[3] | | | | 47.8 | 34.6 | 26.2 | 38.2 |
|
Table 4. Comparison of results for different segmentation algorithms on SUN-RGBD dataset
Method | Module | Model size /MB | Reasoning time /ms |
---|
WRN-CNN | WGCN | PP-Fusion |
---|
Ours | √ | √ | √ | 117 | 42 | Variant 1 | | | | 381 | 76 | Variant 2 | √ | | | 115 | 35 | Variant 3 | | √ | | 187 | 48 | Variant 4 | | | √ | 245 | 51 | FCN[2] | | | | 549 | 43 | SegNet[3] | | | | 126 | 58 |
|
Table 5. Comparison of reasoning time and space complexity for different algorithms