Long-distance Ship Type Recognition Based on Airborne Photon Radar

Shuo WEI; Nanxiang ZHAO; Yihua HU; Wanshun SUN; Biao LIU

doi:10.3788/gzxb20215012.1228001

Acta Photonica Sinica, Volume. 50, Issue 12, 1228001(2021)

Long-distance Ship Type Recognition Based on Airborne Photon Radar

Shuo WEI1...2, Nanxiang ZHAO1,2,*, Yihua HU1,2, Wanshun SUN1,2, and Biao LIU12 |Show fewer author(s)

¹State Key Laboratory of Pulsed Power Laser Technology， Electronic Warfare Academy State Key Laboratory of Pulsed Power Laser Technology ， National University of Defense Technology， Hefei 230037，China

²Advanced Laser Technology Anhui Laboratory， Hefei 230037，China

show less

Abstract Get PDF(in Chinese)

Figures & Tables(14)

Fig. 1. Sea surface point cloud in MABEL data

Download full size

View in Article

Fig. 2. Sea scene detected from the right

Download full size

View in Article

Fig. 3. The scene after removing the sea surface

Download full size

View in Article

Fig. 4. Scenes containing different types of ships

Download full size

View in Article

Fig. 5. Clustering scene

Download full size

View in Article

Fig. 6. Concentric circular division method

Download full size

View in Article

Fig. 7. The angle between the two ends of the ship

Download full size

View in Article

Fig. 8. Models of different types of ships

Download full size

View in Article

Table 1. Circular space division method experiment
View table
View in Article
Table 1. Circular space division method experiment
Rings
Number
1 2 3 4 5
3 83% 91% 91% 75% 83%
4 100% 91% 91% 100% 91%
5 91% 91% 91% 91% 91%
6 83% 83% 91% 83% 83%
7 91% 83% 91% 83% 91%
8 91% 91% 91% 91% 100%
9 91% 91% 91% 91% 91%
10 100% 91% 100% 100% 100%

Table 2. Classification results of routine method vector histogram
View table
View in Article
Table 2. Classification results of routine method vector histogram
Interval
Number
1 2 3 4 5
20 25% 17% 33% 25% 17%
30 17% 17% 17% 17% 17%
45 17% 17% 17% 17% 17%
60 17% 17% 17% 33% 17%

Table 3. Classification results of optimized post-method vector histogram
View table
View in Article
Table 3. Classification results of optimized post-method vector histogram
Interval
Number
1 2 3 4 5
20 67% 58% 67% 75% 75%
30 50% 58% 58% 50% 83%
45 67% 75% 75% 67% 100%
60 67% 50% 67% 58% 58%

Table 4. Partial data of different types of ship models

View table

View in Article

Table 4. Partial data of different types of ship models

Ship type	$M$	Long/m	Width/m	High/m
Cruisers	2.53	183	20	56（25）
Aircraft carriers	2.77	315	75	60
Frigates	2.86	148	16	32（24）
Destroyers	2.61	160	20	30
Fishing ships	2.84	112	30	82.5（30）
Medical ships	2.85	270	34	48
Landing ships	2.63	119	16	26（18）
Crane ships	2.68	170	38	73（28）
Cargo ships	2.82	120	24	40
Scientific research ships	2.73	167	26	32
Container ships	2.97	120	24	40
Cruise ships	2.64	258	100	172
Medium-sized aircraft carriers	2.55	198	38	49

Table 5. Random forest algorithm 7 classification results

View table

View in Article

Table 5. Random forest algorithm 7 classification results

Training number	Number of decision trees	Feature number	Number of misclassifications	Number of correct classifications	Correct rate
1	40	12	0	26	100%
2	40	12	0	26	100%
3 4	40 40	12 12	1 0	25 26	96.15% 100%
5	40	12	0	26	100%
6	40	12	1	25	96.15%
7	40	12	0	26	100%

Table 6. Second classification result

View table

View in Article

Table 6. Second classification result

Training number	Number of decision trees	Feature number	Number of misclassifications	Number of correct classifications	Correct rate
1	40	9	1	25	96.15%
2	40	9	1	25	96.15%
3	40	9	2	24	92.31%
4	40	9	1	25	96.15%
5	40	9	1	25	96.15%
6	40	9	0	26	100%
7	40	9	2	24	92.31%

Tools

Get Citation

Copy Citation Text

Shuo WEI, Nanxiang ZHAO, Yihua HU, Wanshun SUN, Biao LIU. Long-distance Ship Type Recognition Based on Airborne Photon Radar[J]. Acta Photonica Sinica, 2021, 50(12): 1228001

Download Citation

EndNote(RIS)BibTex Plain Text

Set citation alerts for article

Save article for my favorites