Author Affiliations
1Photoelectric Detection Technology Laboratory, Chinese Academy of Sciences, Chengdu, Sichuan 610209, China2Institute of Optics and Electronics, Chinese Academy of Sciences, Chengdu, Sichuan 610209, China3University of Chinese Academy of Sciences, Beijing 100049, Chinashow less
Fig. 1. Complex background in remote sensing images
Fig. 2. Network framework
Fig. 3. Network structure
Fig. 4. Feature weighting method based on grouped convolution
Fig. 5. (a) Schematic diagram of convolutional network receptive field; (b) Object classification strategy based on receptive field
Fig. 6. Object scale distribution of the dataset
Fig. 7. Sample of plane and small-vehicle image of DOTA dataset used in the experiment. (a) Training set; (b) Testing set
Fig. 8. Objects cut and copy flow diagram
Fig. 9. The loss curve of the network trained on the DOTA plane training set
Fig. 10. The loss curve of the network trained on the DOTA small-vehicle training set
Fig. 11. Partial plane test results. Yellow circles represent false alarms and green circles represent missed detection.
Fig. 12. Partial small-vehicle test results. Yellow circles represent false alarms and green circles represent missed detection.
Fig. 13. Model convergence under different initial values of fusion factors
模型 | 参数量M | VGG16 | 138 | ResNet50 | 25.6 | ResNet101 | 44.6 | Ours | 0.49 |
|
Table 1. Parameters of different networks
金字塔层数 | 检测目标尺寸 | 下采样倍数 | 感受野 | 感受野步长 | 感受野/目标尺寸 | 两层 | 1 | 6~25 | 4 | 55 | 4 | 3.5 | 2 | 25~50 | 8 | 95 | 8 | 2.5 | 三层 | 1 | 6~10 | 2 | 23 | 2 | 2.9 | 2 | 10~20 | 4 | 47 | 4 | 3.1 | 3 | 20~50 | 8 | 79 | 8 | 2.3 |
|
Table 2. Receptive field of feature map and corresponding object size parameters
Basic unit | FPN | mAP | Precision | Recall | 两层 | B_11 | - | 86.8 | 76.8 | 88.9 | B_11 | √ | 87.2 | 82.6 | 88.8 | 三层 | B_10 | - | 87.4 | 47.4 | 91.8 | B_10 | √ | 88.5 | 83.8 | 90.4 |
|
Table 3. Detection results of different feature fusion schemes
B_13 | FPN | 分组数量(3) | 特征图通道(channel) | 常数融合因子[0.71,0.87] | mAP | Precision | Recall | √ | - | - | - | - | 80.5 | 63.4 | 82.8 | √ | √ | - | - | - | 82.0 | 81.4 | 85.1 | √ | √ | √ | - | - | 82.3 | 85.1 | 84.5 | √ | √ | - | √ | - | 83.6 | 85.5 | 87.0 | √ | √ | - | - | √ | 82.5 | 82.3 | 85.6 |
|
Table 4. DOTA plane dataset test results under different network configurations
B_12 | FPN | 分组数量(3) | 特征图通道(channel) | 常数融合因子[0.63,1.28] | mAP | Precision | Recall | √ | - | - | - | - | 63.7 | 56.8 | 73.9 | √ | √ | - | - | - | 65.9 | 86.1 | 68.5 | √ | √ | √ | - | - | 66.3 | 83.3 | 68.9 | √ | √ | - | √ | - | 68.7 | 86.4 | 71.7 | √ | √ | - | - | √ | 64.4 | 84.0 | 67.3 |
|
Table 5. DOTA small-vehicle dataset test results under different network configurations
B_10 | FPN | 分组数量(3) | 特征图通道(channel) | 常数融合因子[1.08,1.05] | mAP | Precision | Recall | √ | - | - | - | - | 89.9 | 44.2 | 93.7 | √ | √ | - | - | - | 90.2 | 83.6 | 91.4 | √ | √ | √ | - | - | 90.6 | 84.8 | 92.0 | √ | √ | - | √ | - | 91.0 | 87.7 | 92.4 | √ | √ | - | - | √ | 未收敛 | 未收敛 | 未收敛 |
|
Table 6. Test results of our dataset under different network configurations
数据集 | 尺度 | 目标数量 | 常数融合因子
| DOTA飞机训练集 | [6-12]
| 5503 | 0.87 | [12-30]
| 4807 | | [30-70]
| 3428 | 0.71 | DOTA小汽车训练集 | [6-15]
| 59875 | 1.28 | [15-25]
| 76615 | | [25-60]
| 48203 | 0.63 | 自建数据训练集 | [6-10]
| 4963 | 1.05 | [10-20]
| 5196 | | [20-50]
| 5625 | 1.08 |
|
Table 7. Statistics of the distribution of each scale objects number
Table 8. Influence of initial value of fusion factor on detection performance
模型+数据集 | mAP | Precision | Recall | 推理速度/(s/张) | B_10+FPN+CBAM(自建数据集) | 90.5 | 83.8 | 90.6 | 0.036 | B_10+FPN+自适应融合模块(自建数据集) | 91.0 | 87.7 | 92.4 | 0.027 | B_13+FPN+CBAM(DOTA飞机数据集) | 83.0 | 82.6 | 85.8 | 0.048 | B_13+FPN+自适应融合模块(DOTA飞机数据集) | 83.6 | 85.5 | 87.0 | 0.037 | B_12+FPN+CBAM(DOTA小汽车数据集) | 67.6 | 83.0 | 71.1 | 0.043 | B_12+FPN+自适应融合模块(DOTA小汽车数据集) | 68.7 | 83.3 | 71.7 | 0.034 |
|
Table 9. Influence of CBAM and adaptive fusion module on detection performance
方法 | DOTA飞机数据集(mAP) | DOTA小汽车数据集(mAP) | 自建数据集(mAP) | SSD | 63.4 | 43.3 | 64.4 | RetinaNet | 55.2 | 45.1 | 62.7 | Yolov3-tiny | 70.8 | 58.3 | 74.3 | Faster R-CNN | 73.0 | 59.0 | 88.6 | Ours | 83.6 | 68.7 | 91.0 |
|
Table 10. Comparison of detection performance of different methods
Backbone+数据集 | mAP | ResNet50+FPN(自建数据集) | 88.6 | ResNet50+自适应融合模块(自建数据集) | 89.7 | ResNet50+FPN(DOTA飞机数据集) | 73.0 | ResNet50+自适应融合模块(DOTA飞机数据集) | 73.8 | ResNet50+FPN(DOTA小汽车数据集) | 59.0 | ResNet50+自适应融合模块(DOTA小汽车数据集) | 63.2 |
|
Table 11. Performance of FPN module based on adaptive feature weighted fusion on Faster R-CNN