Fig. 1. Structure of Faster R-CNN

Fig. 2. Structure diagram of Tri-CSAM

Fig. 3. Channel feature maps of ResNet-50 in different nodes. (a) Original image; (b) convolution layer of Conv1;（c）rectified linear unit of Conv1；（d）output layer of Conv2_x

Fig. 4. Schematic of multi-scale receptive field

Fig. 5. Structure of DH

Fig. 6. Structure of regression branch convolution module. (a) Structure of block 1; (b) structure of block 2

Fig. 7. Label visualization of partial dataset

Fig. 8. P-R curves under different IoU thresholds. (a) IoU is 0.50; (b) IoU is 0.75; (c) IoU is 0.90

Fig. 9. Visualization results of network heat map. (a) Small target pedestrian scene of 45° aerial view; (b) medium target vehicles scene of 45° aerial view; (c) small target vehicles scene of 90° aerial view

Fig. 10. Visualization results of aerial image detection. (a) Normal light scene; (b) week light scene; (c) strong light scene