An effective classification method for hyperspectral image with very high resolution based on encoder-decoder architecture

Zhen Zhang, Tao Jiang, Chenxi Liu, Linjing Zhang
2020 IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing  
Hyperspectral images with very high resolution (VHR-HSI) have become considerably valuable due to their abundant spectral and spatial details. Classification of hyperspectral images (HSIs) is a basic and important procedure for diverse applications. However, low interclass spectral variability and high intraclass spectral variability in VHR-HSI, shadows, pedestrians, and low signal-to-noise ratio increase the fuzziness of different categories. To address the known challenges of VHR-HSI
more » ... of VHR-HSI classification, an effective classification method based on encoder-decoder architecture is proposed. The proposed algorithm is an object-level contextual convolution neural network based on an improved residual network backbone with 3-D convolution, which fully considers the spatial-spectral and contextual features of HSIs. Two different spatial resolution aerial HSIs are used as experimental data. The results show that the overall accuracy of the proposed method is improved by 7.42% and 18.82%, respectively, compared to the pixelwise convolution neural network and DeepLabv3 algorithm, which is extraordinarily suitable for HSI classification with very high spatial resolution. Index Terms-Encoder-decoder, hyperspectral image (HSI) with high spatial resolution, image classification, 3-D convolution residual network. interests include remote sensing information processing and analysis, resources and environment remote sensing, and application of remote sensing. Chenxi Liu born in Zhengzhou, Henan province, China, in 1999. He is an undergraduate student with His research interests include machine learning, image classification, and algorithm programming. Linjing Zhang received the B.S. degree in the resource environment and urban-rural planning management from Shandong University of Science and Technology, Qingdao, China, in 2011, the M.S. degree with Remote Sensing Science and Technology in 2014, and the Ph.D. degree in photogrammetry and remote sensing from the State Key Laboratory of Information Engineering in Surveying, Mapping and Remote Sensing, Wuhan University, Wuhan, China, in 2018. Her research interests include remote sensing information processing and analysis, resources and environment remote sensing.
doi:10.1109/jstars.2020.3046245 fatcat:n2qr2nm7xnfq3d7clw73o6eppu