Object Detection in Remote Sensing Images Based on Super-Resolution Hierarchical Fusion Mechanism

Lingfeng YIN; Xudong TONG; Huan NI

doi:10.3969/j.issn.1009-8518.2025.01.011

Journals >Spacecraft Recovery & Remote Sensing >Volume 46 >Issue 1 >Page 123 > Article

Spacecraft Recovery & Remote Sensing
Vol. 46, Issue 1, 123 (2025)

Object Detection in Remote Sensing Images Based on Super-Resolution Hierarchical Fusion Mechanism

Lingfeng YIN, Xudong TONG^*, and Huan NI

Author Affiliations

School of Remote Sensing and Geomatics Engineering, Nanjing University of Information Technology, Nanjing 210044, China

show less

DOI: 10.3969/j.issn.1009-8518.2025.01.011 Cite this Article

Lingfeng YIN, Xudong TONG, Huan NI. Object Detection in Remote Sensing Images Based on Super-Resolution Hierarchical Fusion Mechanism[J]. Spacecraft Recovery & Remote Sensing, 2025, 46(1): 123 Copy Citation Text

show less

Fig. 1. [in Chinese]

Download full size | View in the Article

Fig. 2. [in Chinese]

Download full size | View in the Article

Fig. 3. [in Chinese]

Download full size | View in the Article

Fig. 4. [in Chinese]

Download full size | View in the Article

Fig. 5. [in Chinese]

Download full size | View in the Article

Fig. 6. [in Chinese]

Download full size | View in the Article

Fig. 7. [in Chinese]

Download full size | View in the Article

Fig. 8. [in Chinese]

Download full size | View in the Article

Fig. 9. [in Chinese]

Download full size | View in the Article

Fig. 10. [in Chinese]

Download full size | View in the Article

方法	模态	各分类目标平均精度AP/%								mAP₅₀/%	参数量	FLOPs
方法	模态	轿车	皮卡	露营车	货车	其他	拖拉机	汽艇	面包车	mAP₅₀/%	参数量	FLOPs
YOLOv8s	RGB	78.91	65.29	65.98	54.14	44.46	58.71	31.48	48.97	55.99	11.13×10⁶	9.1×10⁹
	IR	77.05	66.98	68.43	57.90	27.29	40.02	29.76	57.26	53.09	11.13×10⁶	9.1×10⁹
	Multi	77.38	62.39	67.15	53.01	45.28	58.86	32.94	55.54	56.57	11.13×10⁶	9.2×10⁹

Table 1. VEDAI benchmark detection performance

View in the Article

实验	残差融合	单分支增强	超分辅助分支	L1 损失	mAP₅₀/%	参数量	FLOPs
注：√ 表示启用模块或改动。
A	√				70.56	12.49×10⁶	29.6×10⁹
B	√	√			72.94	12.75×10⁶	30.3×10⁹
C	√	√	√		78.42	13.25×10⁶	31.0×10⁹
D	√	√	√	√	79.45	13.25×10⁶	31.2×10⁹

Table 2. Ablation experiment

View in the Article

方法	模态	各分类目标平均精度AP/%								mAP₅₀/%	参数量	FLOPs
方法	模态	轿车	皮卡	露营车	货车	其他	拖拉机	汽艇	面包车	mAP₅₀/%	参数量	FLOPs
YOLOv8s^[24]	RGB	78.91	65.29	65.98	54.14	44.46	58.71	31.48	48.97	55.99	11.13×10⁶	9.1×10⁹
	IR	77.05	66.98	68.43	57.90	27.29	40.02	29.76	57.26	53.09	11.13×10⁶	9.1×10⁹
	Multi	77.38	62.39	67.15	53.01	45.28	58.86	32.94	55.54	56.57	11.13×10⁶	9.2×10⁹
Dual-YOLO^[23]	Multi	80.07	68.01	66.12	51.52	45.76	64.38	21.62	40.93	54.82	12.19×10⁶	19.3×10⁹
DM-YOLO^[25]	RGB	79.68	74.49	77.09	80.97	37.33	70.65	60.84	63.56	68.83	12.37×10⁶	20.4×10⁹
	IR	76.77	74.35	64.74	63.45	45.04	78.12	70.04	77.91	68.18	12.37×10⁶	20.4×10⁹
	Multi	86.71	75.98	66.62	77.17	43.04	62.30	70.75	84.38	70.87	12.38×10⁶	20.5×10⁹
SuperYOLO^[19]	RGB	90.30	82.66	76.69	68.55	53.86	79.48	58.08	70.30	72.49	10.83×10⁶	26.5×10⁹
	IR	87.90	81.39	76.90	61.56	39.39	60.56	46.08	71.00	65.60	10.83×10⁶	26.5×10⁹
	Multi	91.13	85.66	79.30	70.18	57.33	80.41	60.24	76.50	75.09	10.85×10⁶	29.6×10⁹
本文方法	Multi	92.04	88.98	84.98	75.25	63.39	84.67	69.24	77.05	79.45	13.25×10⁶	31.2×10⁹

Table 3. VEDAI accuracy comparison table

View in the Article

方法	模态	各分类目标平均精度AP/%					mAP₅₀/%	参数量	FLOPs
方法	模态	轿车	货车	卡车	公交车	面包车	mAP₅₀/%	参数量	FLOPs
YOLOv8s^[24]	RGB	90.89	43.91	58.87	89.76	43.84	65.45	11.13×10⁶	14.2×10⁹
	IR	91.03	48.82	59.71	92.79	50.92	68.65	11.13×10⁶	14.2×10⁹
	Multi	94.59	54.88	66.14	90.51	58.17	72.86	11.13×10⁶	14.3×10⁹
Dual-YOLO^[23]	Multi	98.16	52.87	65.72	95.77	46.58	71.82	12.19×10⁶	10.5×10⁹
DM-YOLO^[25]	RGB	89.95	48.26	58.27	89.65	44.43	66.11	12.37×10⁶	22.6×10⁹
	IR	97.63	62.33	72.54	93.74	53.94	76.04	12.37×10⁶	22.6×10⁹
	Multi	97.91	64.34	74.63	95.05	57.74	77.93	12.38×10⁶	22.7×10⁹
SuperYOLO^[19]	RGB	86.82	32.53	49.13	82.88	36.68	57.61	10.83×10⁶	25.9×10⁹
	IR	97.35	53.25	65.61	92.30	49.13	71.53	10.83×10⁶	25.9×10⁹
	Multi	97.49	56.05	69.11	93.61	51.79	73.61	10.85×10⁶	28.1×10⁹
本文方法	Multi	98.17	68.61	81.68	96.00	61.98	81.29	13.25×10⁶	26.1×10⁹

Table 4. Drone Vehicle accuracy comparison table

Lingfeng YIN, Xudong TONG, Huan NI. Object Detection in Remote Sensing Images Based on Super-Resolution Hierarchical Fusion Mechanism[J]. Spacecraft Recovery & Remote Sensing, 2025, 46(1): 123

Download Citation

Tools

Save the article for my favorites

Paper Information

微信扫一扫：分享

微信扫一扫：分享