A parallel down-up fusion network for salient object detection in optical remote sensing images

Li，Chongyi1; Cong，Runmin2,3; Guo，Chunle4; Li，Hua5,6; Zhang，Chunjie2,3; Zheng，Feng7; Zhao，Yao2,3

2020-11-20

10.1016/j.neucom.2020.05.108

NEUROCOMPUTING   影响因子和分区

0925-2312

1872-8286

The diverse spatial resolutions, various object types, scales and orientations, and cluttered backgrounds in optical remote sensing images (RSIs) challenge the current salient object detection (SOD) approaches. It is commonly unsatisfactory to directly employ the SOD approaches designed for nature scene images (NSIs) to RSIs. In this paper, we propose a novel Parallel Down-up Fusion network (PDF-Net) for SOD in optical RSIs, which takes full advantage of the in-path low- and high-level features and cross-path multi-resolution features to distinguish diversely scaled salient objects and suppress the cluttered backgrounds. To be specific, keeping a key observation that the salient objects still are salient no matter the resolutions of images are in mind, the PDF-Net takes successive down-sampling to form five parallel paths and perceive scaled salient objects that are commonly existed in optical RSIs. Meanwhile, we adopt the dense connections to take advantage of both low- and high-level information in the same path and build up the relations of cross paths, which explicitly yield strong feature representations. At last, we fuse the multiple-resolution features in parallel paths to combine the benefits of the features with different resolutions, i.e., the high-resolution feature consisting of complete structure and clear details while the low-resolution features highlighting the scaled salient objects. Extensive experiments on the ORSSD dataset demonstrate that the proposed network is superior to the state-of-the-art approaches both qualitatively and quantitatively.

Deep learning Optical remote sensing images Salient object detection

SCI ; EI

英语

其他

Beijing Nova Program[Z201100006820016] ; National Key Research and Development of China[2018AAA0102100] ; National Natural Science Foundation of China[62002014][61532005][U1936212][61972188] ; China Postdoctoral Science Foundation[2020T130050][2019M660438] ; Fundamental Research Funds for the Central Universities[2019RC040]

Computer Science

Computer Science, Artificial Intelligence

WOS:000579808700037

ELSEVIER

20204009293127

Signal sampling ; Image fusion ; Deep learning ; Object recognition ; Object detection

Ergonomics and Human Factors Engineering:461.4 ; Data Processing and Image Processing:723.2 ; Optical Devices and Systems:741.3 ; Statistical Methods:922

COMPUTER SCIENCE

2-s2.0-85091798629

Scopus

1.School of Electrical and Information Engineering,Tianjin University,Tianjin,300072,China
2.Institute of Information Science,Beijing Jiaotong University,Beijing,100044,China
3.Beijing Key Laboratory of Advanced Information Science and Network Technology,Beijing,100044,China
4.College of Computer Science,Nankai University,Tianjin,300350,China
5.School of Software Engineering,Huazhong University of Science and Technology,Wuhan,430074,China
6.Department of Computer Science,City University of Hong Kong,Kowloon,999077,Hong Kong
7.Department of Computer Science and Engineering,Southern University of Science and Technology,Shenzhen,518055,China

Li，Chongyi,Cong，Runmin,Guo，Chunle,et al. A parallel down-up fusion network for salient object detection in optical remote sensing images[J]. NEUROCOMPUTING,2020,415:411-420.

Li，Chongyi.,Cong，Runmin.,Guo，Chunle.,Li，Hua.,Zhang，Chunjie.,...&Zhao，Yao.(2020).A parallel down-up fusion network for salient object detection in optical remote sensing images.NEUROCOMPUTING,415,411-420.

Li，Chongyi,et al."A parallel down-up fusion network for salient object detection in optical remote sensing images".NEUROCOMPUTING 415(2020):411-420.