Author Affiliations
1Shenyang Institute of Automation, Chinese Academy of Sciences, Shenyang, Liaoning 110016, China2Institute for Robotics and Intelligent Manufacturing, Chinese Academy of Sciences, Shenyang, Liaoning 110169, China3Key Laboratory of Opto-Electronic Information Processing, Chinese Academy of Sciences, Shenyang, Liaoning 110016, China4College of Information Science and Engineering, Northeastern University, Shenyang, Liaoning 110819, Chinashow less
Fig. 1. FCN structural diagram
Fig. 2. ResNet basic structural unit
Fig. 3. Diagram of ResNet18 structure
Fig. 4. Main structure of network
Fig. 5. Diagram of N×N channel structure
Fig. 6. Two-channel feature fusion with different scales
Fig. 7. Downsampling and upsampling of location index max pool
Fig. 8. Partial images of data sets and corresponding visual labels
Fig. 9. Partial data set images and their visual mark display after cutting
Fig. 10. Partial original images and display of flipped and rotated images
Fig. 11. Visual classification results of remote sensing images by different classification algorithms
Fig. 12. Visual classification results of channel 1, channel 1+2, and overall structure
Category | Vegetation | Building | Water | Road | Others |
---|
Vegetation | 9225390 | 3939997 | 187818 | 75047 | 281427 | Building | 783726 | 12505800 | 50563 | 126407 | 290737 | Water | 182936 | 9015 | 2069612 | 6761 | 29298 | Road | 20196 | 50490 | 5049 | 3256576 | 176714 | Others | 83475 | 144690 | 8348 | 41738 | 2672437 |
|
Table 1. Obfuscation matrix of classification results of proposed algorithmpixel
Algorithm | Classification accuracy /% | RKappa |
---|
Vegetation | Building | Water | Road | Others | OA |
---|
FCN-8s | 71.88 | 71.43 | 70.09 | 69.97 | 71.23 | 71.30 | 0.6603 | Unet | 80.92 | 80.27 | 80.10 | 79.89 | 80.52 | 80.44 | 0.7522 | SegNet | 83.66 | 83.18 | 82.64 | 82.52 | 83.07 | 83.21 | 0.7810 | Channel 1 | 81.16 | 81.23 | 81.47 | 80.97 | 81.32 | 81.20 | 0.7623 | Channel 1+2 | 89.56 | 89.78 | 89.58 | 89.16 | 89.76 | 89.63 | 0.8406 | Ours | 90.77 | 90.82 | 90.18 | 90.30 | 90.57 | 90.68 | 0.8595 |
|
Table 2. Classification accuracy and RKappa of different algorithms
Algorithm | Total number of parameters /106 | Forward time /ms | Train time /h |
---|
FCN-8s | 134.3 | 221 | 5.56 | Unet | 23.6 | 56 | 4.72 | SegNet | 29.4 | 78 | 4.88 | Channel 1 | 15.3 | 50 | 4.55 | Channel 1+2 | 30.5 | 108 | 5.06 | Ours | 30.5 | 116 | 2.90 |
|
Table 3. Convolution kernel parameters, single forward propagation time, and training time of different algorithms