Super-Resolution Infrared Remote-Sensing Target-Detection Algorithm Based on Deep Learning

Shuo Huang; Yong Hu; MingJian Gu; Cailan Gong; Fuqiang Zheng

doi:10.3788/LOP202158.1610015

Laser & Optoelectronics Progress, Volume. 58, Issue 16, 1610015(2021)

Super-Resolution Infrared Remote-Sensing Target-Detection Algorithm Based on Deep Learning

Shuo Huang^1,2, Yong Hu^1,2、*, MingJian Gu¹, Cailan Gong^1,2, and Fuqiang Zheng^1,2,3

Author Affiliations

¹Shanghai Institute of Technical Physics, Chinese Academy of Sciences, Shanghai 200083, China

²Key Laboratory of Infrared System Detection and Imaging Technology, Chinese Academy of Sciences, Shanghai 200083, China

³University of Chinese Academy of Sciences, Beijing 100049, China

show less

Abstract Get PDF(in Chinese)

Figures & Tables(15)

Fig. 1. Structure of WDSR

Download full size

Fig. 2. Process of sampling

Download full size

Fig. 3. Diagrams of multiscale feature extraction networks. (a) Feature extraction network in Faster RCNN; (b) multiscale feature extraction network

Download full size

Fig. 4. Comparison of target detection results. (a) Before improvement; (b) after improvement

Download full size

Fig. 5. Digram of SROD

Download full size

Fig. 6. Impact of resolution on the accuracy of dataset recognition

Download full size

Fig. 7. Comparison of results. (a) Direct detection results; (b) training with infrared data; (c) after super-resolution reconstruction

Download full size

Fig. 8. Detection results of super-resolution reconstructed image. (a) Bicubic; (b) ScSR; (c) SRCNN; (d) WDSR

Download full size

Fig. 9. SROD ship detection results of the entire image

Download full size

Fig. 10. Comparison of detection results of different methods. (a) Real target; (b) detection result of saliency segmentation; (c) detection result of SROD; (d) detection result of Faster RCNN

Download full size

Fig. 11. Ship targets of different sizes. (a) Large; (b) medium; (c) small

Download full size

Table 1. Structure of ResNet101

View table

Table 1. Structure of ResNet101

Layer name	Output size	Config
Conv1	1/2	7×7, 64, stride 2
Conv2_x	1/4	3×3 max pooling , stride 2
Conv2_x	1/4	$[\begin{array}{l} 1 \times 1 & 64 \\ 3 \times 3 & 64 \\ 1 \times 1 & 256 \end{array}]$ ×3
Conv3_x	1/8	$[\begin{array}{l} 1 \times 1 & 128 \\ 3 \times 3 & 128 \\ 1 \times 1 & 512 \end{array}]$ ×4
Conv4_x	1/16	$[\begin{array}{l} 1 \times 1 & 256 \\ 3 \times 3 & 256 \\ 1 \times 1 & 1024 \end{array}]$ ×23
Conv5_x	1/32	$[\begin{array}{l} 1 \times 1 & 512 \\ 3 \times 3 & 512 \\ 1 \times 1 & 2048 \end{array}]$ ×3
Classifier	1×1	Average pooling, 1000-dFC, Softmax

Table 2. UAV data parameters

View table

Table 2. UAV data parameters

Parameter	Value
Array size	640×480
Wavelength range /mm	7.5~14.0
Pixel size /mm	17
Focal length /mm	35
Angular resolution /mrad	0.68
Data format	U16(Unsigned 16 bits)
Number of pictures taken when the imager sweeps a line	5

Table 3. Detection results
View table
Table 3. Detection results
Algorithm T' N ΔT ΔN P /% R /%
Salience algorithm 196 289 52 93 67.80 79.03
Faster RCNN 180 214 68 34 84.11 72.58
SROD 202 228 46 26 88.59 81.45

Table 4. Target type statistics

View table

Table 4. Target type statistics

Algorithm	Parameter	Number of detected targets			Total
Algorithm	Parameter	Large target	Medium target	Small target	Total
SROD	T'	48	58	96	202
	ΔT	1	3	42	46
	ΔN	10	8	8	26
	N	58	66	104	228
	P /%	82.75	87.87	92.30	88.59
	R /%	97.91	95.08	69.56	81.45
Faster RCNN	T'	43	51	86	180
	ΔT	6	8	54	68
	ΔN	19	9	6	34
	N	62	60	92	214
	P /%	69.35	85	93.47	84.11
	R /%	87.75	86.44	61.42	72.58

Tools

Get Citation

Copy Citation Text

Shuo Huang, Yong Hu, MingJian Gu, Cailan Gong, Fuqiang Zheng. Super-Resolution Infrared Remote-Sensing Target-Detection Algorithm Based on Deep Learning[J]. Laser & Optoelectronics Progress, 2021, 58(16): 1610015

Download Citation

EndNote(RIS)BibTex Plain Text

Set citation alerts for article

Save article for my favorites