Int J Performability Eng ›› 2020, Vol. 16 ›› Issue (1): 59-66.doi: 10.23940/ijpe.20.01.p7.5966

• Orginal Article • Previous Articles     Next Articles

Remote Sensing Image Classification based on Fusion of ATLTP and Tamura Texture Features

Qinggang Wu*(), Yilan Zhao, Qiuwen Zhang, and Bin Jiang   

  1. School of Computer and Communication Engineering, Zhengzhou University of Light Industry, Zhengzhou, 450002, China
  • Submitted on ; Revised on ; Accepted on
  • Contact: Qinggang Wu
  • Supported by:
    This work is supported in part by the National Natural Science Foundation of China under grant No. 61502435, 61771432, 61702464 and 61302118, in part by the Scientific and Technological Project of Henan Province under grant No. 14A520034 and 182102210617, in part by the Doctorate Research Funding of Zhengzhou University of Light Industry under grant No. 2013BSJJ041 and 13501050045, and in part by the young backbone teachers of Zhengzhou University of Light Industry under grant No. 13300093.


Similar remote sensing image classification is often affected by complex backgrounds, illumination changes and noise interference. To improve the classification accuracy of similar remote sensing scenes, a novel image algorithm is proposed based on the fusion of global and local texture features. Specifically, the proposed algorithm is composed of three steps. Firstly, adaptive threshold local ternary pattern (ATLTP) and Tamura texture features of remote sensing images are extracted separately. Secondly, both texture features are fused together in a cascade manner to mitigate the interference of complex backgrounds in remote sensing images. Finally, on the basis of the fused texture features, the remote sensing images are classified by Support Vector Machine (SVM). To evaluate the performance of the proposed algorithm, extensive experiments are conducted on two standard remote sensing datasets of UC Merced Land-Use and NWPU-RESISC45. The effectiveness of the proposed algorithm is validated by the average classification accuracy improvement of 8.94%.

Key words: remote sensing image, feature fusion, adaptive threshold local ternary pattern (ATLTP), Tamura feature, support vector machine