Figure 1.
A three-dimensional tensor: (a) column fiber; (b) row fiber; (c) tube fiber.
Figure 1.
A three-dimensional tensor: (a) column fiber; (b) row fiber; (c) tube fiber.
Figure 2.
The t-product of and .
Figure 2.
The t-product of and .
Figure 3.
The transpose tensor.
Figure 3.
The transpose tensor.
Figure 4.
The identity tensor .
Figure 4.
The identity tensor .
Figure 5.
The f-diagonal tensor.
Figure 5.
The f-diagonal tensor.
Figure 6.
The t-SVD result of .
Figure 6.
The t-SVD result of .
Figure 7.
Graph of the low-rank function, nuclear norm, LogDet function, Laplace function and SRF of scalars.
Figure 7.
Graph of the low-rank function, nuclear norm, LogDet function, Laplace function and SRF of scalars.
Figure 8.
Tensor completion method test results on simulation dataset DS1. One area of interest (red frame) is enlarged for detailed comparison. (a) The original images of different bands of DS1 with different sampling ratios (because there are too many bands, bands 56 and 57 are selected for display when the sampling rate is 10% (first row); bands 66 and 67 are selected for display when the sampling rate is 20% (fourth row); and bands 73 and 74 are displayed when the sampling rate is 30% (seventh row)). (b) The sampling data images of the original images. From the sampling data images, the characteristic information of the retained pixels after random sampling of the specific bands can be seen. (c–g) are (in order) the tensor reconstruction results with sampling rates of 10%, 20% and 30% by HaLRTC, TNN, LogDet-TC, Laplace-TC and the proposed method. The first, fourth and seventh rows are the reconstruction results with sampling rates of 10%, 20% and 30%, respectively. The second, fifth and eighth rows show the difference images between the original image and the reconstruction results by HaLRTC, TNN, LogDet-TC, Laplace-TC and the proposed method with various sampling rates. The third, sixth and ninth rows are gray distribution histograms of the corresponding difference images.
Figure 8.
Tensor completion method test results on simulation dataset DS1. One area of interest (red frame) is enlarged for detailed comparison. (a) The original images of different bands of DS1 with different sampling ratios (because there are too many bands, bands 56 and 57 are selected for display when the sampling rate is 10% (first row); bands 66 and 67 are selected for display when the sampling rate is 20% (fourth row); and bands 73 and 74 are displayed when the sampling rate is 30% (seventh row)). (b) The sampling data images of the original images. From the sampling data images, the characteristic information of the retained pixels after random sampling of the specific bands can be seen. (c–g) are (in order) the tensor reconstruction results with sampling rates of 10%, 20% and 30% by HaLRTC, TNN, LogDet-TC, Laplace-TC and the proposed method. The first, fourth and seventh rows are the reconstruction results with sampling rates of 10%, 20% and 30%, respectively. The second, fifth and eighth rows show the difference images between the original image and the reconstruction results by HaLRTC, TNN, LogDet-TC, Laplace-TC and the proposed method with various sampling rates. The third, sixth and ninth rows are gray distribution histograms of the corresponding difference images.
Figure 9.
Test results of the tensor completion method on simulation dataset DS2. One area of interest (red frame) is enlarged for detailed comparison. (a) The original images of different bands of DS2 with different sampling ratios (bands 56 and 57 are selected for display when the sampling rate is 10% (first row); bands 92 and 94 are selected for display when the sampling rate is 20% (fourth row); bands 93 and 95 are selected for display when the sampling rate is 30% (seventh row). (b) The sampling data images of the original images with sampling rates of 10%, 20% and 30%, respectively. (c–g) are the tensor reconstruction results of HaLRTC, TNN, LogDet-TC, Laplace-TC and the proposed method. The first, fourth and seventh rows are the reconstruction results for sampling rates of 10%, 20% and 30%. The second, fifth and eighth rows show the difference images between the original image and the reconstruction results by HaLRTC, TNN, LogDet-TC, Laplace-TC and the proposed method with various sampling rates. The third, sixth and ninth rows are the gray distribution histograms of the corresponding difference images.
Figure 9.
Test results of the tensor completion method on simulation dataset DS2. One area of interest (red frame) is enlarged for detailed comparison. (a) The original images of different bands of DS2 with different sampling ratios (bands 56 and 57 are selected for display when the sampling rate is 10% (first row); bands 92 and 94 are selected for display when the sampling rate is 20% (fourth row); bands 93 and 95 are selected for display when the sampling rate is 30% (seventh row). (b) The sampling data images of the original images with sampling rates of 10%, 20% and 30%, respectively. (c–g) are the tensor reconstruction results of HaLRTC, TNN, LogDet-TC, Laplace-TC and the proposed method. The first, fourth and seventh rows are the reconstruction results for sampling rates of 10%, 20% and 30%. The second, fifth and eighth rows show the difference images between the original image and the reconstruction results by HaLRTC, TNN, LogDet-TC, Laplace-TC and the proposed method with various sampling rates. The third, sixth and ninth rows are the gray distribution histograms of the corresponding difference images.
Figure 10.
Tensor completion method test results on DS3. One area of interest (red frame) is enlarged for detailed comparison. (a) The original images of different bands of DS3 with different sampling ratios (bands 32 and 99 are selected for display when the sampling rate is 10% (first row); bands 5 and 18 are selected for display when the sampling rate is 20% (fourth row); bands 42 and 51 are selected for display when the sampling rate is 30% (seventh row). (b) The sampling data images of the original images with sampling rates of 10%, 20% and 30%, respectively. (c–g) are (in order) the tensor reconstruction results of HaLRTC, TNN, LogDet-TC, Laplace-TC and the proposed method for sampling rates of 10%, 20% and 30%. The first, fourth and seventh rows are the reconstruction results for sampling rates of 10%, 20% and 30%. The second, fifth and eighth rows show the difference images between the original image and the reconstruction results by HaLRTC, TNN, LogDet-TC, Laplace-TC and the proposed method with various sampling rates. The third, sixth and ninth rows are the gray distribution histograms of the corresponding difference images.
Figure 10.
Tensor completion method test results on DS3. One area of interest (red frame) is enlarged for detailed comparison. (a) The original images of different bands of DS3 with different sampling ratios (bands 32 and 99 are selected for display when the sampling rate is 10% (first row); bands 5 and 18 are selected for display when the sampling rate is 20% (fourth row); bands 42 and 51 are selected for display when the sampling rate is 30% (seventh row). (b) The sampling data images of the original images with sampling rates of 10%, 20% and 30%, respectively. (c–g) are (in order) the tensor reconstruction results of HaLRTC, TNN, LogDet-TC, Laplace-TC and the proposed method for sampling rates of 10%, 20% and 30%. The first, fourth and seventh rows are the reconstruction results for sampling rates of 10%, 20% and 30%. The second, fifth and eighth rows show the difference images between the original image and the reconstruction results by HaLRTC, TNN, LogDet-TC, Laplace-TC and the proposed method with various sampling rates. The third, sixth and ninth rows are the gray distribution histograms of the corresponding difference images.
Figure 11.
Distribution map of the ground object types in example 4.
Figure 11.
Distribution map of the ground object types in example 4.
Figure 12.
Tensor completion method test results on the distribution map of ground object types from the Remote Sensing Imaging Processing Center of the National University of Singapore. (a) The original images of different bands of simulation dataset 4 with different sampling ratios (bands 22 and 23 are selected for display at sampling rates of 10%, 20% and 30% (first, fourth and seventh rows, respectively)). (b) The sampling data images of the original images with sampling rates of 10%, 20% and 30%, respectively. (c–g) are the tensor reconstruction results for sampling rates of 10%, 20% and 30% by HaLRTC, TNN, LogDet-TC, Laplace-TC and the proposed method. The first, fourth and seventh rows are the reconstruction results for sampling rates of 10%, 20% and 30%. The second, fifth and eighth rows show the difference images between the original image and the reconstruction results by HaLRTC, TNN, LogDet-TC, Laplace-TC and the proposed method with various sampling rates. The third, sixth and ninth rows are the gray distribution histograms of the corresponding difference images.
Figure 12.
Tensor completion method test results on the distribution map of ground object types from the Remote Sensing Imaging Processing Center of the National University of Singapore. (a) The original images of different bands of simulation dataset 4 with different sampling ratios (bands 22 and 23 are selected for display at sampling rates of 10%, 20% and 30% (first, fourth and seventh rows, respectively)). (b) The sampling data images of the original images with sampling rates of 10%, 20% and 30%, respectively. (c–g) are the tensor reconstruction results for sampling rates of 10%, 20% and 30% by HaLRTC, TNN, LogDet-TC, Laplace-TC and the proposed method. The first, fourth and seventh rows are the reconstruction results for sampling rates of 10%, 20% and 30%. The second, fifth and eighth rows show the difference images between the original image and the reconstruction results by HaLRTC, TNN, LogDet-TC, Laplace-TC and the proposed method with various sampling rates. The third, sixth and ninth rows are the gray distribution histograms of the corresponding difference images.
Figure 13.
The results on the AVIRIS cuprite dataset. (a) The original images of different bands of the AVIRIS cuprite dataset with different sampling ratios (bands 72 and 74 are selected for display when the sampling rate is 10% (first row); bands 67 and 68 are selected for display when the sampling rate is 20% (fourth row); bands 65 and 68 are selected for display when the sampling rate is 30% (seventh row). (b) The sampling data images of the original images with sampling rates of 10%, 20% and 30%, respectively. (c–g) are the tensor reconstruction results for sampling rates of 10%, 20% and 30% by HaLRTC, TNN, LogDet-TC, Laplace-TC and the proposed method. The first, fourth and seventh rows are the reconstruction results for sampling rates of 10%, 20% and 30%. The second, fifth and eighth rows show the difference images between the original image and the reconstruction results by HaLRTC, TNN, LogDet-TC, Laplace-TC and the proposed method with various sampling rates. The third, sixth and ninth rows are the gray distribution histograms of the corresponding difference images.
Figure 13.
The results on the AVIRIS cuprite dataset. (a) The original images of different bands of the AVIRIS cuprite dataset with different sampling ratios (bands 72 and 74 are selected for display when the sampling rate is 10% (first row); bands 67 and 68 are selected for display when the sampling rate is 20% (fourth row); bands 65 and 68 are selected for display when the sampling rate is 30% (seventh row). (b) The sampling data images of the original images with sampling rates of 10%, 20% and 30%, respectively. (c–g) are the tensor reconstruction results for sampling rates of 10%, 20% and 30% by HaLRTC, TNN, LogDet-TC, Laplace-TC and the proposed method. The first, fourth and seventh rows are the reconstruction results for sampling rates of 10%, 20% and 30%. The second, fifth and eighth rows show the difference images between the original image and the reconstruction results by HaLRTC, TNN, LogDet-TC, Laplace-TC and the proposed method with various sampling rates. The third, sixth and ninth rows are the gray distribution histograms of the corresponding difference images.
Table 1.
The relevant information of the data in 5 experiments.
Table 1.
The relevant information of the data in 5 experiments.
| Data Source | Data Size (Height × Width × Band) |
---|
Example 1 | Generated from nine end members randomly selected from the subset generated from the NASA Johnson Space Center (NASA-JSC) spectral characteristics database | 100 × 100 × 100 |
Example 2 | Generated from four end members randomly selected from generated from the United States Geological Survey (USGS) digital spectrum database | 100 × 100 × 224 |
Example 3 | Generated by randomly selecting five end members from | 75 × 75 × 100 |
Example 4 | Distribution map of ground object types from the Remote Sensing Imaging Processing Center of the National University of Singapore | 278 × 329 × 100 |
Example 5 | The AVIRIS Cuprite dataset | 350 × 350 × 188 |
Table 2.
Ground object types, their colors and composition end members.
Table 2.
Ground object types, their colors and composition end members.
Ground Object Type Number (Color) | Ground Object Type | Composition End Members (%) |
---|
1 (Dark brown) | Pure water | End member 1 (60), end member 10 (40) |
2 (Fuchsia) | Forest | End member 2 (90), end member 7 (10) |
3 (Yellow-green) | Shrub | End member 3 (50), end member 8 (50) |
4 (Light blue) | Grass | End member 4 (100) |
5 (Dark gray) | Soil, man-made buildings | End member 5 (70), end member 9 (30) |
6 (Navy blue) | Turbid water, soil, man-made buildings | End member 6 (40), end member 9 (30), end member 5 (30) |
7 (Light blue-green) | Soil, man-made buildings | End member 5 (50), end member 9 (50) |
8 (Dark blue-green) | Soil, man-made buildings | End member 5 (40), end member 9 (60) |
Table 3.
The PSNR and SSIM values of the five methods.
Table 3.
The PSNR and SSIM values of the five methods.
Dataset | Sampling Rate | HaLRTC | TNN | LogDet-TC | Laplace-TC | Proposed |
---|
PSNR | SSIM | PSNR | SSIM | PSNR | SSIM | PSNR | SSIM | PSNR | SSIM |
---|
DS1 | 10% | 19.1810 | 0.5427 | 26.1529 | 0.7779 | 26.5367 | 0.7730 | 27.1079 | 0.7811 | 27.6988 | 0.8027 |
20% | 24.3083 | 0.7850 | 30.4836 | 0.8771 | 31.3059 | 0.8830 | 31.9637 | 0.8908 | 32.3647 | 0.8979 |
30% | 28.7637 | 0.9037 | 33.8098 | 0.9271 | 34.9760 | 0.9347 | 35.3474 | 0.9380 | 35.6564 | 0.9409 |
DS2 | 10% | 44.3918 | 0.9915 | 50.2451 | 0.9965 | 52.0375 | 0.9975 | 52.1378 | 0.9975 | 52.5568 | 0.9979 |
20% | 47.8194 | 0.9961 | 59.3216 | 0.9995 | 61.3278 | 0.9997 | 59.3125 | 0.9995 | 61.9718 | 0.9997 |
30% | 54.1652 | 0.9990 | 66.4177 | 0.9999 | 67.7105 | 0.9999 | 68.0190 | 0.9999 | 68.5685 | 0.9999 |
DS3 | 10% | 46.8033 | 0.9928 | 47.5930 | 0.9897 | 50.5077 | 0.9940 | 50.9990 | 0.9943 | 67.4867 | 1.0000 |
20% | 50.9409 | 0.9974 | 54.7000 | 0.9978 | 57.3828 | 0.9986 | 57.0897 | 0.9986 | 95.5115 | 1.0000 |
30% | 54.4479 | 0.9986 | 61.0524 | 0.9994 | 63.5759 | 0.9996 | 63.4314 | 0.9996 | 98.4993 | 1.0000 |
Distribution map of ground object types | 10% | 21.5421 | 0.4777 | 27.8932 | 0.7478 | 28.0606 | 0.7472 | 28.2599 | 0.7715 | 28.5770 | 0.7949 |
20% | 24.9645 | 0.6679 | 32.2982 | 0.8828 | 33.1070 | 0.8808 | 33.1114 | 0.8976 | 33.3183 | 0.9038 |
30% | 26.8058 | 0.7725 | 35.8089 | 0.9394 | 36.4996 | 0.9364 | 36.8591 | 0.9475 | 37.0572 | 0.9502 |
AVIRIS Cuprite | 10% | 49.3208 | 0.4318 | 53.7352 | 0.7869 | 55.8124 | 0.8232 | 59.7162 | 0.8979 | 62.2725 | 0.9173 |
20% | 53.4043 | 0.7048 | 56.6647 | 0.8804 | 57.3858 | 0.8224 | 64.9149 | 0.9502 | 67.0668 | 0.9565 |
30% | 56.6848 | 0.8435 | 59.6989 | 0.9183 | 60.7367 | 0.8908 | 68.3113 | 0.9679 | 69.9921 | 0.9707 |
Table 4.
Percentage of pixels within a small range of pixel values (centered on 0) of the difference images between the original image and the recovered images using five tensor completion methods.
Table 4.
Percentage of pixels within a small range of pixel values (centered on 0) of the difference images between the original image and the recovered images using five tensor completion methods.
Dataset | Sampling Rate | Difference Range of Pixel Value | Percentage of Pixels Occupied |
---|
HaLRTC | TNN | LogDet-TC | Laplace-TC | Proposed |
---|
DS1 | 10% | [−0.15,0.15] | 86.330% | 99.805% | 99.870% | 99.920% | 99.940% |
20% | [−0.10,0.10] | 92.820% | 99.935% | 99.965% | 99.985% | 99.990% |
30% | [−0.05,0.05] | 85.450% | 99.300% | 99.775% | 99.800% | 99.860% |
DS2 | 10% | [−0.01,0.01] | 89.145% | 90.415% | 93.535% | 96.225% | 97.935% |
20% | [−0.07,0.07] | 69.225% | 98.090% | 99.085% | 98.875% | 99.925% |
30% | [−0.05,0.05] | 87.980% | 99.795% | 99.905% | 99.975% | 99.990% |
DS3 | 10% | [−0.02,0.02] | 97.013% | 98.027% | 98.951% | 98.996% | 100% |
20% | [−0.01,0.01] | 97.867% | 98.818% | 99.093% | 99.493% | 100% |
30% | [−0.003,0.003] | 94.347% | 96.631% | 97.173% | 97.493% | 100% |
Distribution map of ground object types | 10% | [−0.10,0.10] | 80.146% | 98.202% | 98.367% | 98.746% | 98.912% |
20% | [−0.10,0.10] | 90.904% | 99.873% | 99.957% | 99.944% | 99.955% |
30% | [−0.10,0.10] | 94.792% | 99.993% | 99.997% | 99.998% | 99.999% |
AVIRIS Cuprite | 10% | [−400,400] | 88.529% | 97.606% | 99.294% | 99.971% | 99.997% |
20% | [−100,100] | 59.607% | 80.892% | 78.311% | 98.905% | 99.904% |
30% | [−50,50] | 55.267% | 71.592% | 69.236% | 96.605% | 99.255% |
Table 5.
The number of iterations and running time of the five methods.
Table 5.
The number of iterations and running time of the five methods.
Dataset | Method | HaLRTC | TNN | LogDet-TC | Laplace-TC | Proposed |
---|
DS1 | Number of iterations | 240 | 348 | 207 | 202 | 196 |
Time | 8.80 | 61.54 | 53.24 | 51.44 | 46.75 |
DS2 | Number of iterations | 261 | 380 | 178 | 170 | 163 |
Time | 9.42 | 64.09 | 43.61 | 40.25 | 36.12 |
DS3 | Number of iterations | 313 | 374 | 200 | 186 | 181 |
Time | 6.56 | 36.75 | 26.83 | 23.71 | 22.82 |
Distribution map of ground object types | Number of iterations | 362 | 365 | 202 | 194 | 187 |
Time | 121.06 | 634.11 | 548.77 | 526.93 | 510.04 |
AVIRIS Cuprite | Number of iterations | 245 | 282 | 181 | 176 | 167 |
Time | 121.13 | 719.70 | 574.42 | 529.66 | 492.13 |