Precise object detection using adversarially augmented local/global feature fusion. (September 2020)

• Record Type: Journal Article
• Authors: Han, Xiaobing; He, Tiantian; Ong, Yew-Soon; Zhong, Yanfei
• Is Part Of: Engineering applications of artificial intelligence. Volume 94(2020)
• Publication Date: 2020-09
• Subjects: High spatial resolution (HSR) remote sensing imagery -- Geospatial object detection -- Super resolution generative adversarial network -- Data augmentation -- Local/global feature fusion; Engineering -- Data processing -- Periodicals; Artificial intelligence -- Periodicals; Expert systems (Computer science) -- Periodicals; Ingénierie -- Informatique -- Périodiques; Intelligence artificielle -- Périodiques; Systèmes experts (Informatique) -- Périodiques; Artificial intelligence; Engineering -- Data processing; Expert systems (Computer science); Periodicals; 620.00285
• DOI: 10.1016/j.engappai.2020.103710
• Languages: English
• ISSNs: 0952-1976

Abstract

Abstract: Object detection, which aims at recognizing or locating the objects of interest in remote sensing imagery with high spatial resolutions (HSR), plays a significant role in many real-world scenarios, e.g., environment monitoring, urban planning, civil infrastructure construction, disaster rescuing, and geographic image retrieval. As a long-lasting challenging problem in both machine learning and geoinformatics communities, many approaches have been proposed to tackle it. However, previous methods always overlook the abundant information embedded in the HSR remote sensing images. The effectiveness of these methods, e.g., accuracy of detection, is therefore limited to some extent. To overcome the mentioned challenge, in this paper, we propose a novel two-phase deep framework, dubbed GLGOD-Net, to effectively detect meaningful objects in HSR images. GLGOD-Net firstly attempts to learn the enhanced deep representations from super-resolution image data. Fully utilizing the augmented image representations, GLGOD-Net then learns the fused representations into which both local and global latent features are implanted. Such fused representations learned by GLGOD-Net can be used to precisely detect different objects in remote sensing images. The proposed framework has been extensively tested on a real-world HSR image dataset for object detection and has been compared with several strong baselines. The remarkable experimental results validate the effectiveness of GLGOD-Net. The success of GLGOD-Net not only advances the cutting-edge of image data analytics, but also promotes the corresponding applicability of deep learning in remote sensing imagery.