Unmanned Aerial Vehicle Detection Based on ASRPCA Fused with Five-Frame Difference

Na Li; Kuangang Fan; Yahui Liu; Qinghua Ouyang

doi:10.3788/LOP202158.2015007

Journals >Laser & Optoelectronics Progress >Volume 58 >Issue 20 >Page 2015007 > Article

Laser & Optoelectronics Progress
Vol. 58, Issue 20, 2015007 (2021)

Unmanned Aerial Vehicle Detection Based on ASRPCA Fused with Five-Frame Difference

Na Li^1、2, Kuangang Fan^1、2、*, Yahui Liu^1、2, and Qinghua Ouyang^1、2

Author Affiliations

¹School of Electrical Engineering and Automation, Jiangxi University of Science and Technology, Ganzhou, Jiangxi 341000, China

²Key Laboratory of Magnetic Levitation Technology in Jiangxi Province, Ganzhou, Jiangxi 341000, China

show less

DOI: 10.3788/LOP202158.2015007 Cite this Article Set citation alerts

Na Li, Kuangang Fan, Yahui Liu, Qinghua Ouyang. Unmanned Aerial Vehicle Detection Based on ASRPCA Fused with Five-Frame Difference[J]. Laser & Optoelectronics Progress, 2021, 58(20): 2015007 Copy Citation Text

show less

Fig. 1. Flow chart of improved algorithm

Download full size

Fig. 2. Comparison results of UAV detection using different algorithms under different background sequences

Download full size

Fig. 3. Gaussian noise detection results with different variances

Download full size

Video	Five-Frame Difference+			ViBe+			Optical Flow+			GMM+			TVRPCA			Proposed algorithm
Video	R	P	F	R	P	F	R	P	F	R	P	F	R	P	F	R	P	F
(a)	0.85	0.91	0.89	0.92	0.75	0.83	0.89	0.83	0.86	0.62	0.90	0.73	0.87	0.94	0.90	0.91	0.93	0.92
(b)	0.46	0.83	0.59	0.88	0.74	0.80	0.81	0.63	0.71	0.82	0.66	0.73	0.86	0.84	0.85	0.92	0.91	0.91
(c)	0.58	0.79	0.67	0.86	0.70	0.77	0.87	0.71	0.78	0.63	0.77	0.70	0.85	0.86	0.85	0.89	0.85	0.87
(d)	0.53	0.87	0.66	0.84	0.73	0.78	0.92	0.72	0.81	0.63	0.81	0.71	0.86	0.81	0.83	0.91	0.92	0.91
(e)	0.37	0.88	0.52	0.89	0.62	0.73	0.90	0.89	0.89	0.59	0.80	0.68	0.89	0.90	0.89	0.94	0.93	0.93
(f)	0.79	0.85	0.82	0.71	0.80	0.75	0.92	0.49	0.64	0.11	0.57	0.18	0.84	0.83	0.83	0.87	0.85	0.86
(g)	0.51	0.86	0.64	0.81	0.79	0.80	0.79	0.80	0.79	0.21	0.87	0.33	0.86	0.89	0.87	0.93	0.88	0.90

Table 1. Measured value P,R,F of various algorithms

Algorithm	Variance	R	P	F
	0.001	0.46	0.81	0.59
Five-Frame Difference+	0.005	0.46	0.78	0.58
	0.01	0.46	0.54	0.50
	0.02	0.47	0.36	0.41
	0.001	0.82	0.66	0.73
GMM+	0.005	0.82	0.62	0.71
	0.01	0.81	0.53	0.64
	0.02	0.81	0.50	0.62
	0.001	0.88	0.74	0.80
ViBe+	0.005	0.88	0.63	0.73
	0.01	0.87	0.55	0.67
	0.02	0.85	0.43	0.57
	0.001	0.91	0.88	0.89
TVRPCA	0.005	0.90	0.85	0.87
	0.01	0.90	0.82	0.85
	0.02	0.89	0.78	0.83
	0.001	0.86	0.63	0.71
Optical Flow+	0.005	0.86	0.63	0.71
	0.01	0.86	0.63	0.71
	0.02	0.86	0.63	0.71
	0.001	0.92	0.90	0.91
Proposed algorithm	0.005	0.92	0.89	0.90
	0.01	0.91	0.88	0.89
	0.02	0.91	0.87	0.89

Table 2. Measured value P, R, F of Gaussian noise with different variances

Algorithm	(a)	(b)	(c)	(d)	(e)	Average
Five-Frame Difference+	24.80	25.23	27.02	24.24	26.28	26.30
ViBe+	98.78	93.43	95.87	96.13	96.41	95.12
Optical Flow+	101.14	102.62	101.98	104.34	102.82	103.27
GMM+	76.59	75.31	76.59	76.23	73.72	75.69
TVRPCA	256.30	236.45	255.23	232.27	246.46	226.37
Proposed algorithm	31.16	30.79	30.27	31.30	30.03	30.71

Table 3. Comparison of running time of different algorithms unit: s

Na Li, Kuangang Fan, Yahui Liu, Qinghua Ouyang. Unmanned Aerial Vehicle Detection Based on ASRPCA Fused with Five-Frame Difference[J]. Laser & Optoelectronics Progress, 2021, 58(20): 2015007

Download Citation

Set citation alerts for the article

Tools

Set citation alerts for the article

Save the article for my favorites

Paper Information