A novel two-stage deep learning-based small-object detection using hyperspectral images

• Published in: Optical review (Tokyo, Japan) Japan), 2019-12, Vol.26 (6), p.597-606
• Main Authors: Yan, Lu, Yamaguchi, Masahiro, Noro, Naoki, Takara, Yohei, Ando, Fuminori
• Format: Article
• Language: English
• Subjects: Atomic; Lasers; Microwaves; Molecular; Optical and Plasma Physics; Optical Devices; Optics; Photonics; Physics; Physics and Astronomy; Quantum Optics; Regular Paper; RF and Optical Engineering
• ISSN: 1340-6000; 1349-9432
• DOI: 10.1007/s10043-019-00528-0

Hyperspectral imaging has drawn significant attention in recent years, and its application to object detection and classification is currently an important research topic. However, finding a method to accurately identify objects that only occupy a very small part of an image area remains to be a challenge. In this paper, a novel two-stage deep learning-based hyperspectral neural network (2SHyperNet) suitable for human detection from the sea surface is proposed. The method combines spatial and spectral information of hyperspectral images. Pixel-wise spectral information is used in the first stage to obtain first-stage classification results, and then the results are combined with spatial information to help eliminate unlikely regions, thus, improving the detection accuracy. The method is tested on a data set of real-world airborne hyperspectral images, and its performance is compared with those of several conventional methods. The results show that the proposed method outperforms current state-of-the-art methods.