3D-CNN and Autoencoder Based Gas Detection in Hyperspectral Images

Creative Commons License

Ozdemir O. B., Koz A.

IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, vol.16, pp.1474-1482, 2023 (SCI-Expanded, Scopus) identifier identifier

  • Publication Type: Article / Article
  • Volume: 16
  • Publication Date: 2023
  • Doi Number: 10.1109/jstars.2023.3235781
  • Journal Name: IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
  • Journal Indexes: Science Citation Index Expanded (SCI-EXPANDED), Scopus, Aerospace Database, Aquatic Science & Fisheries Abstracts (ASFA), Compendex, Geobase, INSPEC, Directory of Open Access Journals, Civil Engineering Abstracts
  • Page Numbers: pp.1474-1482
  • Keywords: Hyperspectral imaging, Gases, Three-dimensional displays, Temperature distribution, Convolutional neural networks, Sulfur, Neural networks, Autoencoders, convolutional neural networks (CNNs), gas detection, hyperspectral unmixing, IDENTIFICATION, PLUMES
  • Open Archive Collection: AVESIS Open Access Collection
  • Middle East Technical University Affiliated: Yes

Abstract

AuthorThe detection of gas emission levels is a crucial problem for ecology and human health. Hyperspectral image analysis offers many advantages over traditional gas detection systems with its detection capability from safe distances. Observing that the existing hyperspectral gas detection methods in the thermal range neglect the fact that the captured radiance the in longwave infrared (LWIR) spectrum is better modeled as a mixture of the radiance of background and target gases, we propose a deep learning-based hyperspectral gas detection method in this paper, which combines unmixing and classification. The proposed method first converts the radiance data to luminance-temperature data. Then, a 3D CNN and autoencoder-based network, which is specially designed for unmixing, is applied to the resulting data to acquire abundances and endmembers for each pixel. Finally, the detection is achieved by a three-layer fully connected network to detect the target gases at each pixel based on the extracted endmember spectra and abundance values. The superior performance of the proposed method with respect to the conventional hyperspectral gas detection methods using spectral angle mapper (SAM) and adaptive cosine estimator (ACE) is verified with LWIR hyperspectral images including Methane and Sulphur Dioxide gases. In addition, the ablation study with respect to different combinations of the proposed structure including direct classification and unmixing methods has revealed the contribution of the proposed system.