Lightweight Object Detection Method for Optical Remote Sensing Image

Module	YOLOv5s	YOLOv5m	YOLOv5l	YOLOv5x
depth_multiple	0.33	0.67	1.0	1.33
width_multiple	0.50	0.75	1.0	1.25
Number of C3 in backbone	1，3，3	2，6，6	3，9，9	4，12，12
Number of C3 in neck	1	2	3	4
Number of Conv	32，64，128，256，512	48，96，192，384，768	64，128，256，512，1024	80，160，320，640，1280

Table 2. Comparison between YOLOv5s and Ghost-YOLOv5s
View table
Table 2. Comparison between YOLOv5s and Ghost-YOLOv5s
Model Parameters /MB Model size /MB $m A P$ Precision Recall
YOLOv5s 7.23 14.2 0.692 0.93 0.82
Ghost-YOLOv5s 5.9 11.6 0.676 0.929 0.82

Table 3. AP for different types of targets in YOLOv5s and Ghost-YOLOv5s

View table

Table 3. AP for different types of targets in YOLOv5s and Ghost-YOLOv5s

Type of targets	AP for different types of targets （YOLOv5s）	AP for different types of targets （Ghost-YOLOv5s）
All classes mAP	0.692	0.676
plane	0.942	0.939
baseball_diamond	0.791	0.795
bridge	0.543	0.518
ground_track_field	0.653	0.589
small_vehicle	0.600	0.586
large_vehicle	0.806	0.799
ship	0.878	0.871
tennis_court	0.943	0.926
basketball_court	0.683	0.657
storage_tank	0.795	0.774
soccer_ball_field	0.547	0.570
roundabout	0.719	0.691
harbor	0.819	0.825
swimming_pool	0.711	0.718
helicopter	0.638	0.532
container_crane	0.012	0.019

Table 4. Comparison between Ghost-YOLOv5s and FA-YOLO
View table
Table 4. Comparison between Ghost-YOLOv5s and FA-YOLO
Model Parameters /MB Model size /MB $m A P$ Precision Recall
Ghost-YOLOv5s 5.9 11.6 0.676 0.929 0.82
FA-YOLO 3.75 7.64 0.673 0.947 0.79

Table 5. Comparison before and after adding FA module
View table
Table 5. Comparison before and after adding FA module
Model Parameters /MB Model size /MB $m A P$ Precision Recall
FA-YOLO （without FA） 3.73 7.54 0.662 0.94 0.78
FA-YOLO （with FA） 3.75 7.64 0.673 0.947 0.79

Table 6. Comparison of network models under different pruning thresholds
View table
Table 6. Comparison of network models under different pruning thresholds
$m A P$ Number of finetune Pruning threshold Parameters /MB Model size /MB
0.647 20 0.05 3.43 6.99
0.646 20 0.1 3.18 6.49
0.648 20 0.15 2.55 5.29
0.577 20 0.2 1.41 3.11
0.424 20 0.25 0.85 2.05

Table 7. Comparison between Ghost-YOLOv5s and LW-YOLO
View table
Table 7. Comparison between Ghost-YOLOv5s and LW-YOLO
Model Precision Recall $m A P$ Parameters /MB Model size /MB Mean inference time /s
YOLOv5s 0.93 0.82 0.692 7.23 14.2 5.4
LW-YOLO 0.943 0.79 0.648 2.55 5.29 5.2

Table 8. LW-YOLO network AP and mAP for different types of targets

View table

Table 8. LW-YOLO network AP and mAP for different types of targets

Type of targets	AP for different types of targets
All classes mAP	0.648
plane	0.916
baseball_diamond	0.712
bridge	0.473
ground_track_field	0.514
small_vehicle	0.570
large_vehicle	0.787
ship	0.852
tennis_court	0.933
basketball_court	0.639
storage_tank	0.738
soccer_ball_field	0.470
roundabout	0.615
harbor	0.774
swimming_pool	0.681
helicopter	0.587
container_crane	0.110

Table 9. Statistics of number of targets in each category in training set

View table

Table 9. Statistics of number of targets in each category in training set

Type of targets	Number of targets
plane	8072
baseball_diamond	412
bridge	2075
ground_track_field	331
small_vehicle	126501
large_vehicle	22218
ship	32973
tennis_court	2425
basketball_court	529
storage_tank	5346
soccer_ball_field	338
roundabout	437
harbor	6016
swimming_pool	2181
helicopter	635
container_crane	142

Tools

Get Citation

Copy Citation Text

Hao Wang, Zengshan Yin, Guohua Liu, Denghui Hu, Shuang Gao. Lightweight Object Detection Method for Optical Remote Sensing Image[J]. Laser & Optoelectronics Progress, 2022, 59(22): 2210004

Download Citation

EndNote(RIS)BibTex Plain Text

Set citation alerts for article

Save article for my favorites