Location of Typhoon Center Based on Multi-Scale Mosaic Mask R-CNN

Zongsheng Zheng; Jiahui Zhao; Peng Lu; Guoliang Zou; Zhenhua Wang

doi:10.3788/LOP213379

Journals >Laser & Optoelectronics Progress >Volume 60 >Issue 10 >Page 1010009 > Article

Laser & Optoelectronics Progress
Vol. 60, Issue 10, 1010009 (2023)

Location of Typhoon Center Based on Multi-Scale Mosaic Mask R-CNN

Zongsheng Zheng, Jiahui Zhao^*, Peng Lu, Guoliang Zou, and Zhenhua Wang

Author Affiliations

College of Information Technology, Shanghai Ocean University, Shanghai 201306, China

show less

DOI: 10.3788/LOP213379 Cite this Article Set citation alerts

Zongsheng Zheng, Jiahui Zhao, Peng Lu, Guoliang Zou, Zhenhua Wang. Location of Typhoon Center Based on Multi-Scale Mosaic Mask R-CNN[J]. Laser & Optoelectronics Progress, 2023, 60(10): 1010009 Copy Citation Text

show less

Fig. 1. Model architecture diagram

Download full size

Fig. 2. Original labeled data. (a) Sample 1; (b) sample 2; (c) sample 3; (d) sample 4

Download full size

Fig. 3. Fused data

Download full size

Fig. 4. Satellite cloud image data. (a) Sample 1; (b) sample 2; (c) sample 3; (d) sample 4

Download full size

Fig. 5. Sample drawing of detect results. (a) Sample 1; (b) sample 2; (c) sample 3; (d) sample 4

Download full size

Fig. 6. Loss function figure of Mask R-CNN model

Download full size

Fig. 7. Loss function figures of Mask R-CNN model combined with data augmentation. (a) Proposed multi-scale mosaic; (b) Cutout; (c) CutMix; (d) mosaic

Download full size

Fig. 8. Deep learning method for locating typhoon center. (a) Faster R-CNN; (b) YOLOv3; (c) Mask R-CNN

Download full size

Fig. 9. Fitting diagrams of real coordinates and segmented coordinates of model. (a) HAISHEN; (b) VAMCO

Download full size

Level of scale	Radius size	Number of pictures
Small	$r$ < 1.43	1467
Middle	1.43 ≤ $r$ < 1.90	1467
Large	$r$ ≥ 1.90	1466

Table 1. Scale division of typhoon eye

Hyperparameter	Value
NMS-thresh	0.45
Score-thresh	0.5
Maximum iterations	40000
Model checkpoint	2
Learning rate	10^-4-10^-6
Weight decay	5×10^-4
GPU number	1
Input size	128×128

Table 2. Universal hyperparameter settings

Scale combination	Number	MSE	Mean MSE	MIoU	Mean MIoU	MPA	Mean MPA	FPS	Mean FPS
Master model	1	3802		0.9086		0.8959		20.4
Large+Middle	1	2154	2554	0.9454	0.9421	0.9263	0.9218	17.1	20.6
	2	2981		0.9384		0.9170		23.3
	3	2527		0.9426		0.9221		21.5
Large+Small	1	3290	3415	0.9322	0.9313	0.9098	0.9115	19.4	21.4
	2	3747		0.9270		0.9061		22.7
	3	3208		0.9348		0.9186		22.2
Middle+Small	1	3685	4176	0.9259	0.9151	0.8836	0.8896	20.8	20.7
	2	4761		0.9151		0.8908		19.8
	3	4082		0.9044		0.8944		21.5
Large+Middle+Small	1	3125	3355	0.9187	0.9222	0.8968	0.9043	22.1	20
	2	3588		0.9221		0.9047		18.7
	3	3351		0.9258		0.9113		19.2

Table 3. Results of multi-scale experiments

Model	MIoU^S	MIoU^M	MIoU^L	MPA^S	MPA^M	MPA^L
Mask R-CNN	0.8880	0.9145	0.9233	0.8830	0.8831	0.9216
Mask R-CNN+Proposed multi-scale mosaic	0.9305	0.9469	0.9489	0.9090	0.9197	0.9367

Table 4. Comparison of wind eye segmentation results at different scales

Model	Data augmentation method	MSE	MIoU	MPA	FPS
Mask R-CNN		3802	0.9086	0.8959	20.4
	Proposed multi-scale mosaic	2554	0.9421	0.9218	20.6
	Cutout	5373	0.8569	0.8247	22.8
	CutMix	4006	0.9135	0.9061	17.0
	mosaic	3249	0.9207	0.9074	15.4

Table 5. Experimental results of each data augmentation

Model	Mean error		Mean variance
Model	Longitude	Latitude	Longitude	Latitude
Faster R-CNN	0.31	0.26	0.055	0.046
YOLOv3	0.28	0.25	0.043	0.039
Mask R-CNN+Proposed multi-scale mosaic	0.17	0.19	0.028	0.025

Table 6. Comparison of location accuracy of typhoon center

Zongsheng Zheng, Jiahui Zhao, Peng Lu, Guoliang Zou, Zhenhua Wang. Location of Typhoon Center Based on Multi-Scale Mosaic Mask R-CNN[J]. Laser & Optoelectronics Progress, 2023, 60(10): 1010009

Download Citation

Set citation alerts for the article

Tools

Set citation alerts for the article

Save the article for my favorites

Paper Information