Object Detection For Remote Sensing Image Based on Multiscale Feature Fusion Network

Tingting Tian; Jun Yang

doi:10.3788/LOP202259.1628003

Laser & Optoelectronics Progress, Volume. 59, Issue 16, 1628003(2022)

Object Detection For Remote Sensing Image Based on Multiscale Feature Fusion Network

Tingting Tian^1,2,3 and Jun Yang^1,2,3、*

Author Affiliations

¹Faculty of Geomatics, Lanzhou Jiaotong University, Lanzhou 730070, Gansu , China

²National-Local Joint Engineering Research Center of Technologies and Applications for National Geographic State Monitoring, Lanzhou 730070, Gansu , China

³Gansu Provincial Engineering Laboratory for National Geographic State Monitoring, Lanzhou 730070, Gansu , China

show less

Abstract Get PDF(in Chinese)

Figures & Tables(13)

Fig. 1. Architecture of proposed object detection model

Download full size

Fig. 2. Comparison between convolution and dilated convolution. (a) General convolution; (b) dilated convolution

Download full size

Fig. 3. Feature fusion network. (a) FPN; (B) PANet

Download full size

Fig. 4. Multi-dimensional attention module

Download full size

Fig. 5. Detection results on RSOD dataset. (a) Aircraft; (b) oiltank; (c) overpass; (d) playground

Download full size

Fig. 6. Detection results on DOTA dataset. (a) PL; (b) GTF and SBF; (c) BR; (d) BD; (e) LV and SV; (f) RA; (g) HA; (h) ST; (i) SH; (j) BC and TC; (k) SP; (l) HC

Download full size

Fig. 7. Examples of miss detection and error detection. (a) Miss detection; (b) error detection

Download full size

Table 1. Detection results on RSOD dataset
View table
Table 1. Detection results on RSOD dataset
Dataset Aircraft Oiltank Overpass Playground mAP
RSOD 81.02 90.77 100 100 92.95

Table 2. Detection results on DOTA dataset
View table
Table 2. Detection results on DOTA dataset
Dataset PL BD BR GTF SV LV SH TC BC ST SBF RA HA SP HC mAP
DOTA 89.68 84.39 52.12 72.71 64.49 67.07 77.45 90.11 83.98 86.01 64.03 63.33 74.45 67.74 62.87 73.39

Table 3. Experimental comparison of different FPN on RSOD dataset
View table
Table 3. Experimental comparison of different FPN on RSOD dataset
Type Aircraft Oiltank Overpass Playground mAP
FPN 78.86 90.48 99.73 100.00 92.26
FPN++ 81.02 90.77 100.00 100.00 92.95

Table 4. Experimental comparison of different FPN on DOTA dataset

View table

Table 4. Experimental comparison of different FPN on DOTA dataset

Type	PL	BD	BR	GTF	SV	LV	SH	TC	BC	ST	SBF	RA	HA	SP	HC	mAP
FPN	88.81	84.33	50.98	72.45	62.71	65.35	75.34	89.96	81.16	84.07	53.26	63.33	72.24	66.29	60.11	71.36
FPN++	89.68	84.39	52.12	72.71	64.49	67.07	77.45	90.11	83.98	86.01	55.03	63.33	74.45	67.74	62.87	72.86

Table 5. Accuracy comparison of different algorithms on RSOD dataset

View table

Table 5. Accuracy comparison of different algorithms on RSOD dataset

Algorithm	aircraft	oiltank	overpass	playground	mAP
R-FCN	71.48	90.23	76.84	97.70	84.07
Deformable R-FCN	71.50	90.26	81.48	99.53	85.70
Faster R-CNN	71.90	90.90	100.00	100.00	90.70
RFN	79.10	90.50	100.00	99.70	92.30
MDCF²Det	81.02	90.77	100.00	100.00	92.95

Table 6. Accuracy comparison of different algorithms on DOTA dataset

View table

Table 6. Accuracy comparison of different algorithms on DOTA dataset

Algorithm	PL	BD	BR	GTF	SV	LV	SH	TC	BC	ST	SBF	RA	HA	SP	HC	mAP
YOLO v2	76.90	33.87	22.73	34.88	38.73	32.02	52.37	61.65	48.54	33.91	29.27	36.83	36.44	38.26	11.61	39.20
R-FCN	79.33	44.26	36.58	53.53	39.38	34.15	47.29	45.66	47.74	65.84	37.92	44.23	50.64	50.64	34.90	47.24
CenterFPANet	88.74	71.52	48.95	52.06	48.55	73.37	61.14	90.53	57.63	84.06	66.64	62.71	73.33	57.63	42.76	65.29
FPN	88.70	75.10	52.60	59.20	69.40	78.80	84.50	90.60	81.30	82.60	52.50	62.10	76.60	66.30	60.10	72.00
ICN	90.00	77.70	53.40	73.30	73.50	65.00	78.20	90.80	79.10	84.80	57.20	62.11	73.45	70.22	58.08	72.45
FMSSD	89.11	81.51	48.22	67.94	69.23	73.56	76.87	90.71	82.67	73.33	52.65	67.52	72.37	80.57	60.15	72.43
MDCF²Det	89.68	84.39	52.12	72.71	64.49	67.07	77.45	90.11	83.98	86.01	55.03	63.33	74.45	67.74	62.87	72.86

Tools

Get Citation

Copy Citation Text

Tingting Tian, Jun Yang. Object Detection For Remote Sensing Image Based on Multiscale Feature Fusion Network[J]. Laser & Optoelectronics Progress, 2022, 59(16): 1628003

Download Citation

EndNote(RIS)BibTex Plain Text

Set citation alerts for article

Save article for my favorites