Opto-Electronic Engineering, Volume. 49, Issue 4, 210363(2022)
Small object detection based on multi-scale feature fusion using remote sensing images
Figures & Tables(24)
Fig. 5. (a) Schematic diagram of convolutional network receptive field; (b) Object classification strategy based on receptive field
Fig. 7. Sample of plane and small-vehicle image of DOTA dataset used in the experiment. (a) Training set; (b) Testing set
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
Table 1. Parameters of different networks
View tableView in ArticleTable 1. Parameters of different networks
模型 参数量M VGG16 138 ResNet50 25.6 ResNet101 44.6 Ours 0.49
Table 2. Receptive field of feature map and corresponding object size parameters
View tableView in ArticleTable 2. Receptive field of feature map and corresponding object size parameters
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 3. Detection results of different feature fusion schemes
View tableView in ArticleTable 3. Detection results of different feature fusion schemes
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 4. DOTA plane dataset test results under different network configurations
View tableView in ArticleTable 4. DOTA plane dataset test results under different network configurations
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 5. DOTA small-vehicle dataset test results under different network configurations
View tableView in ArticleTable 5. DOTA small-vehicle 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 6. Test results of our dataset under different network configurations
View tableView in ArticleTable 6. Test results of our dataset 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 7. Statistics of the distribution of each scale objects number
View tableView in ArticleTable 7. Statistics of the distribution of each scale objects number
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 8. Influence of initial value of fusion factor on detection performance
View tableView in ArticleTable 8. Influence of initial value of fusion factor on detection performance
融合因子初始值 mAP 1 83.6 随机初始化 80.7
Table 9. Influence of CBAM and adaptive fusion module on detection performance
View tableView in ArticleTable 9. Influence of CBAM and adaptive fusion module 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 10. Comparison of detection performance of different methods
View tableView in ArticleTable 10. Comparison of detection performance of different methods
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 11. Performance of FPN module based on adaptive feature weighted fusion on Faster R-CNN
View tableView in ArticleTable 11. Performance of FPN module based on adaptive feature weighted fusion on Faster R-CNN
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
Tools
Get Citation
Copy Citation Text
Liang Ma, Yutao Gou, Tao Lei, Lei Jin, Yixuan Song. Small object detection based on multi-scale feature fusion using remote sensing images[J]. Opto-Electronic Engineering, 2022, 49(4): 210363
Paper Information
Category:
Received: Nov. 15, 2021
Accepted: --
Published Online: May. 24, 2022
The Author Email: Lei Tao (taoleiyan@ioe.ac.cn)
© Copyright 2018-2021 | Chinese Laser Press.
All Rights Reserved 沪ICP备15018463号-20