Vehicle detection method based on remote sensing image fusion of superpixel and multi-modal sensing network

Yuanfeng LIAN; Guangyang LI; Shaochen SHEN

doi:10.37188/OPE.20233106.0905

Optics and Precision Engineering, Volume. 31, Issue 6, 905(2023)

Vehicle detection method based on remote sensing image fusion of superpixel and multi-modal sensing network

Yuanfeng LIAN1...2,*, Guangyang LI1 and Shaochen SHEN1 |Show fewer author(s)

Author Affiliations

¹China University of Petroleum， Beijing02249， China

²Beijing Key Laboratory of Petroleum Data Mining， China University of Petroleum.， Beijing1049， China

show less

Abstract Get PDF(in Chinese)

Figures & Tables(13)

Fig. 1. Overall network structure diagram

Download full size

View in Article

Fig. 2. Region adjacent graph

Download full size

View in Article

Fig. 3. Superpixel segmentation remote sensing image results under differentλp

Download full size

View in Article

Fig. 4. Superpixel segmentation of remote sensing image results

Download full size

View in Article

Fig. 5. Precision and recall are compared between the proposed model and other method

Download full size

View in Article

Fig. 6. Comparison of segmentation results of this method and other methods on ISPRS Potsdam dataset

Download full size

View in Article

Fig. 7. Comparison of segmentation results of this method and other methods on ISPRS Vaihingen dataset

Download full size

View in Article

Fig. 8. Influence of OPT-FPN module on local details of vehicle detection

Download full size

View in Article

Fig. 9. Influence of multi-mode fusion module on local details of vehicle detection

Download full size

View in Article

Table 1. Proposed model was compared with other models on the ISPRS Potsdam dataset

View table

View in Article

Table 1. Proposed model was compared with other models on the ISPRS Potsdam dataset

模型	Surface	Building	Low-veg	Tree	Car	MIoU	mF1	OA
FCN-32s	76.14	89.81	72.01	68.98	66.84	74.76	84.48	87.15
FCN-8s	77.52	90.34	72.62	65.98	77.32	76.76	85.54	87.44
U-net	77.20	91.16	73.23	69.00	79.29	77.98	86.67	87.84
SegNet	72.84	87.99	67.68	60.33	75.00	72.77	82.76	84.93
PSPNet	79.16	91.73	73.37	69.76	75.61	77.92	86.61	88.26
DeepLabv3+	79.60	91.21	75.48	70.33	78.19	78.96	87.28	88.92
G-FRNet	85.16	95.55	80.56	76.77	81.53	83.91	90.65	91.94
our	85.72	96.00	81.91	76.82	82.59	84.61	91.05	92.39

Table 1. [in Chinese]

View table

View in Article

Table 1. [in Chinese]

输入：遥感光学图像和高程数据

输出：光学图像区域合并结果

1：分别读入光学图像和高程图像，得到的预分割结果 $A$ ， $B$ ；

2：使用定义9对遥感影像预分割结果进行分裂操作；

3：构建二分图；

3.1：设置 $V = I^{P} ⋃ P ⋃ S$ ；

3.2： $W = \emptyset$ ；

3.3：for $i = 1, \dots, m + n$ do

3.4： for $j = 1, \dots, n$ do

3.5：计算 $W_{i j}$ ；

3.6： $W = W ⋃ w_{i j}$ ；

3.7： end for

3.8：end for

4：使用Transfer Cuts算法计算分割向量 $V$ ；

5：基于向量 $V$ 对 $I$ 进行区域融合。

Table 2. Proposed model was compared with other models on the ISPRS Vaihingen dataset

View table

View in Article

Table 2. Proposed model was compared with other models on the ISPRS Vaihingen dataset

模型	Surface	Building	Low-veg	Tree	Car	background	MIoU	mF1	OA
FCN-32s	73.12	83.47	59.99	73.51	41.20	10.50	56.97	68.76	84.10
FCN-8s	78.30	85.53	59.87	74.60	61.36	18.28	62.99	74.56	85.91
U-net	79.09	85.83	63.95	76.06	64.61	17.92	64.58	75.67	86.76
SegNet	73.48	82.49	57.24	72.81	43.75	1.23	55.17	65.91	83.43
PSPNet	78.21	87.15	62.58	75.56	56.13	19.34	63.16	74.71	86.44
DeepLabv3+	79.48	87.90	62.90	75.94	64.12	19.62	64.99	76.10	86.98
G-FRNet	80.13	89.33	68.15	79.41	52.68	42.50	68.70	80.26	88.48
our	86.13	93.50	64.94	75.34	71.38	58.12	74.90	85.11	89.66

Table 3. Results of ablation experiment
View table
View in Article
Table 3. Results of ablation experiment
Models Surface Building Low-veg Tree Car mIoU
$N 1$ 85.72 96.00 81.91 76.82 82.59 84.61
$N 2$ 85.10 95.76 80.55 75.94 81.16 83.70
$M 1$ 85.72 96.00 81.91 76.82 82.59 84.61
$M 2$ 83.26 94.05 77.42 73.66 81.35 81.95

Tools

Get Citation

Copy Citation Text

Yuanfeng LIAN, Guangyang LI, Shaochen SHEN. Vehicle detection method based on remote sensing image fusion of superpixel and multi-modal sensing network[J]. Optics and Precision Engineering, 2023, 31(6): 905

Download Citation

EndNote(RIS)BibTex Plain Text

Set citation alerts for article

Save article for my favorites