Aiming at the problem of aircraft detection in complex scene, a novel aircraft detection algorithm based on eigen-decomposition and scattering similarity for PolSAR image is proposed. Firstly, Image denoising is performed by using typical scattering difference index (TSDI) filter. Then, region of interest (ROI) containing airport runway and apron is extracted with the characteristics of scattering power, where suspected aircraft targets may exist. Finally, detection statistics are constructed with eigenvalue and scattering similarity parameters to determine true aircraft from suspected targets. Experimental results with real PolSAR data acquired by USA NASA UAVSAR system show that the proposed method can detect aircrafts in complex scene with low resolution effectively.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Aircraft Detection Based on Eigen Decomposition and Scattering Similarity for PolSAR Image


    Contributors:
    Han, Ping (author) / Han, Binbin (author) / Shi, Qingyan (author) / Song, Tinghua (author) / Lu, Xiaoguang (author) / Zhang, Zhe (author)


    Publication date :

    2018-09-01


    Size :

    951279 byte





    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English




    Impact of G4U and 7-component target decomposition on PolSAR image semantic segmentation

    Turkar, Varsha / Checker, Juhi / De, Shaunak et al. | Elsevier | 2022


    A Novel Image Similarity Measure Based on Greatest and Smallest Eigen Fuzzy Sets

    ferdinando di martino / salvatore sessa | BASE | 2023

    Free access

    Automatic Detection of Airport Runway Area Based on Super-Pixel PolSAR Image Classification

    Han, Ping / Lin, Zeshan / Lu, Xiaoguang et al. | Springer Verlag | 2019


    Automatic Detection of Airport Runway Area Based on Super-Pixel PolSAR Image Classification

    Han, Ping / Lin, Zeshan / Lu, Xiaoguang et al. | British Library Conference Proceedings | 2019