Object Detection in Remote Sensing Images Using Multiscale Convolutional Neural Networks

Qunli Yao; Xian Hu; Hong Lei

doi:10.3788/AOS201939.1128002

Acta Optica Sinica, Volume. 39, Issue 11, 1128002(2019)

Object Detection in Remote Sensing Images Using Multiscale Convolutional Neural Networks

Qunli Yao^1,2、*, Xian Hu^1,2, and Hong Lei¹

¹Department of Space Microwave Remote Sensing Systems, Institute of Electronics, Chinese Academy of Sciences, Beijing 100190, China

²School of Electronics, Electrical and Communication Engineering, University of Chinese Academy of Sciences, Beijing 100049, China

show less

Abstract Get PDF(in Chinese)

Figures & Tables(8)

Fig. 1. Target detection framework of MSCNN

Download full size

Fig. 2. Structures of EFPN and dilated bottleneck. (a) Structure of EFPN module; (b) dilated bottleneck structure; (c) dilated bottleneck structure with 1×1 Conv

Download full size

Fig. 3. Network structure of EFPN-NoProj

Download full size

Fig. 4. Visual detection results of MSCNN

Download full size

Table 1. Definition of bounding box areas based on distribution of instance scales
View table
Table 1. Definition of bounding box areas based on distribution of instance scales
Small Medium Large
(0,60] (60,120] (120,+¥)

Table 2. Comparison of the detection precision of different algorithms on NWPU VHR-10 dataset

View table

Table 2. Comparison of the detection precision of different algorithms on NWPU VHR-10 dataset

Method	RICNN^[25]	FRCN-VGG-16^[16]	YOLO^[15]	SSD^[13]	R-FCN^[26]	FRCN-Deform^[27]	FPN^[18]	MSDN^[28]	MSCNN
Airplane	0.884	0.830	0.874	0.956	0.961	0.983	0.964	0.998	0.994
Ship	0.773	0.776	0.847	0.937	0.983	0.892	0.931	0.972	0.953
Storage tank	0.853	0.525	0.427	0.617	0.725	0.817	0.914	0.838	0.918
Baseball diamond	0.881	0.963	0.931	0.995	0.994	0.984	0.947	0.991	0.963
Tennis court	0.408	0.629	0.658	0.860	0.907	0.859	0.944	0.973	0.954
Basketball court	0.585	0.688	0.870	0.944	0.978	0.927	0.959	0.999	0.967
Ground track field	0.867	0.984	0.975	0.987	0.981	0.988	0.990	0.986	0.993
Harbor	0.686	0.819	0.800	0.950	0.924	0.946	0.921	0.972	0.955
Bridge	0.615	0.793	0.903	0.966	0.934	0.947	0.838	0.927	0.972
Vehicle	0.711	0.639	0.704	0.745	0.884	0.816	0.900	0.901	0.933
mAP	0.726	0.764	0.799	0.894	0.928	0.917	0.931	0.956	0.960

Table 3. Ablation experimental parameters of MSCNN
View table
Table 3. Ablation experimental parameters of MSCNN
Backbone Average precision
I_OU=0.5:0.95 I_OU=0.5 I_OU=0.75 Small Medium Large
RetinaNet 0.690 0.945 0.809 0.532 0.559 0.682
EFPN 0.706 0.960 0.824 0.547 0.578 0.701
EFPN-NoProj 0.700 0.950 0.819 0.544 0.562 0.698

Table 4. Average precision and average recall under different IOU thresholds and different bounding box areas

View table

Table 4. Average precision and average recall under different IOU thresholds and different bounding box areas

Backbone	Average precision			Average precision(I_OU =0.5:0.95)			Average recall(I_OU=0.5:0.95)
Backbone	I_OU=0.5:0.95	I_OU=0.5	I_OU=0.75	Small	Medium	Large	Small	Medium	Large
RetinaNet	0.690	0.945	0.809	0.532	0.559	0.682	0.573	0.586	0.754
MSCNN	0.706	0.960	0.824	0.547	0.578	0.701	0.600	0.605	0.755
EFPN-NoProj	0.700	0.950	0.819	0.544	0.562	0.698	0.597	0.600	0.753

Tools

Get Citation

Copy Citation Text

Qunli Yao, Xian Hu, Hong Lei. Object Detection in Remote Sensing Images Using Multiscale Convolutional Neural Networks[J]. Acta Optica Sinica, 2019, 39(11): 1128002

Download Citation

EndNote(RIS)BibTex Plain Text

Set citation alerts for article

Save article for my favorites

Paper Information

Category: Remote Sensing and Sensors

Received: Apr. 8, 2019

Accepted: Jul. 26, 2019

Published Online: Nov. 6, 2019

The Author Email: Yao Qunli (yaoqunli15@mails.ucas.ac.cn)

DOI:10.3788/AOS201939.1128002

Topics

laser devices and laser physics

Lasers and Laser Optics

Laser physics

laser manufacturing

Instrumentation, Measurement and Metrology

Table 1. Definition of bounding box areas based on distribution of instance scales

Table 1. Definition of bounding box areas based on distribution of instance scales

Table 2. Comparison of the detection precision of different algorithms on NWPU VHR-10 dataset

Table 2. Comparison of the detection precision of different algorithms on NWPU VHR-10 dataset

Table 3. Ablation experimental parameters of MSCNN

Table 3. Ablation experimental parameters of MSCNN

Table 4. Average precision and average recall under different IOU thresholds and different bounding box areas

Table 4. Average precision and average recall under different IOU thresholds and different bounding box areas